diff --git a/.gitignore b/.gitignore index 35cac98..00cd6bf 100644 --- a/.gitignore +++ b/.gitignore @@ -19,11 +19,11 @@ benchmarks/gpu/*.json !benchmarks/gpu/.gitkeep # OCR outputs -outputs/ +# outputs/ # Generated structured logs (legacy logs directly under logs/ remain tracked) -logs/input/ -logs/verify/ -logs/image/ -logs/batch/ -logs/pdf/ +# logs/input/ +# logs/verify/ +# logs/image/ +# logs/batch/ +# logs/pdf/ diff --git a/data/images/合同01.jpg b/data/images/合同01.jpg new file mode 100644 index 0000000..3fbf38d Binary files /dev/null and b/data/images/合同01.jpg differ diff --git a/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-155523.log b/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-155523.log new file mode 100644 index 0000000..79f8a8c --- /dev/null +++ b/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-155523.log @@ -0,0 +1,15 @@ +2026-07-16 15:55:23 | INFO | pid=30556 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\化肥买卖合同_GF_2000_0102-cpu-20260716-155523.log +2026-07-16 15:55:23 | INFO | pid=30556 | COMMAND_STARTED command=input input=data\documents\化肥买卖合同　GF—2000—0102.pdf device=cpu log=D:\Dev\ocr-VL1.6\logs\input\化肥买卖合同_GF_2000_0102-cpu-20260716-155523.log +2026-07-16 15:55:23 | INFO | pid=30556 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf kind=pdf mode=hybrid +2026-07-16 15:55:23 | INFO | pid=30556 | PDF_PREFLIGHT_COMPLETED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf page_count=2 selected_pages=2 output=D:\Dev\ocr-VL1.6\outputs\化肥买卖合同_GF_2000_0102 mode=hybrid +2026-07-16 15:55:23 | INFO | pid=30556 | PDF_OPENED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf mode=hybrid seconds=0.001 dpi=144 +2026-07-16 15:55:23 | INFO | pid=30556 | TASK_PLAN mode=hybrid total_pages=2 selected_pages=2 completed_before=0 pending_pages=2 +2026-07-16 15:55:23 | INFO | pid=30556 | PAGE_START page=1 position=1/2 mode=hybrid +2026-07-16 15:55:23 | INFO | pid=30556 | PAGE_ROUTED page=1 source=text reason=usable_text_layer text_chars=251 printable_ratio=1.0000 content_ratio=0.8566 density=500.841 text_extract_seconds=0.009 +2026-07-16 15:55:23 | INFO | pid=30556 | PAGE_FINISHED page=1 status=completed source=text text_extract_seconds=0.009 render_seconds=0.000 ocr_seconds=0.000 export_seconds=0.002 state_save_seconds=0.032 total_seconds=0.011 eta_seconds=0.011 progress=1/2 +2026-07-16 15:55:23 | INFO | pid=30556 | PAGE_START page=2 position=2/2 mode=hybrid +2026-07-16 15:55:23 | INFO | pid=30556 | PAGE_ROUTED page=2 source=text reason=usable_text_layer text_chars=371 printable_ratio=1.0000 content_ratio=0.8194 density=740.287 text_extract_seconds=0.001 +2026-07-16 15:55:23 | INFO | pid=30556 | PAGE_FINISHED page=2 status=completed source=text text_extract_seconds=0.001 render_seconds=0.000 ocr_seconds=0.000 export_seconds=0.003 state_save_seconds=0.004 total_seconds=0.004 eta_seconds=0.000 progress=2/2 +2026-07-16 15:55:23 | INFO | pid=30556 | TASK_COMPLETED status=completed mode=hybrid selected_pages=2 text_pages=2 ocr_pages=0 failed_pages=[] model_used=False model_initialized_during_task=False model_available=False model_init_seconds=0.000 text_extract_total_seconds=0.010 render_total_seconds=0.000 ocr_total_seconds=0.000 task_total_seconds=0.062 +2026-07-16 15:55:23 | INFO | pid=30556 | PDF_COMPLETED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf status=completed text_pages=2 ocr_pages=0 failed_pages=[] model_used=False model_initialized_during_task=False file_total_seconds=0.070 output=D:\Dev\ocr-VL1.6\outputs\化肥买卖合同_GF_2000_0102 +2026-07-16 15:55:23 | INFO | pid=30556 | PROGRAM_COMPLETED input=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf kind=pdf status=completed file_seconds=0.070 program_total_seconds=0.070 diff --git a/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-161926.log b/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-161926.log new file mode 100644 index 0000000..2f62bae --- /dev/null +++ b/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-161926.log @@ -0,0 +1,29 @@ +2026-07-16 16:19:26 | INFO | pid=32836 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\化肥买卖合同_GF_2000_0102-cpu-20260716-161926.log +2026-07-16 16:19:26 | INFO | pid=32836 | COMMAND_STARTED command=input input=data\documents\化肥买卖合同　GF—2000—0102.pdf device=cpu log=D:\Dev\ocr-VL1.6\logs\input\化肥买卖合同_GF_2000_0102-cpu-20260716-161926.log +2026-07-16 16:19:26 | INFO | pid=32836 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf kind=pdf mode=hybrid +2026-07-16 16:19:26 | ERROR | pid=32836 | FILE_FAILED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf error=输出目录已存在: D:\Dev\ocr-VL1.6\outputs\pdfs\化肥买卖合同_GF_2000_0102；请使用 --resume 或 --overwrite +Traceback (most recent call last): + File "D:\Dev\ocr-VL1.6\ocr_app\commands.py", line 350, in run_input + result = process_single_file( + input_path, + ...<4 lines>... + run_image_warmup=True, + ) + File "D:\Dev\ocr-VL1.6\ocr_app\commands.py", line 332, in process_single_file + return process_pdf_file( + path, + ...<3 lines>... + batch_root=batch_root, + ) + File "D:\Dev\ocr-VL1.6\ocr_app\commands.py", line 233, in process_pdf_file + preflight = preflight_pdf( + pdf_path=path, + ...<5 lines>... + overwrite=args.overwrite, + ) + File "D:\Dev\ocr-VL1.6\ocr_app\pdf.py", line 201, in preflight_pdf + pdf_path, output_root = validate_pdf_request(pdf_path, output_root, resume=resume, overwrite=overwrite) + ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "D:\Dev\ocr-VL1.6\ocr_app\pdf.py", line 187, in validate_pdf_request + raise FileExistsError(f"输出目录已存在: {document_dir}；请使用 --resume 或 --overwrite") +FileExistsError: 输出目录已存在: D:\Dev\ocr-VL1.6\outputs\pdfs\化肥买卖合同_GF_2000_0102；请使用 --resume 或 --overwrite diff --git a/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-162010.log b/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-162010.log new file mode 100644 index 0000000..be0a234 --- /dev/null +++ b/logs/input/化肥买卖合同_GF_2000_0102-cpu-20260716-162010.log @@ -0,0 +1,15 @@ +2026-07-16 16:20:10 | INFO | pid=23172 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\化肥买卖合同_GF_2000_0102-cpu-20260716-162010.log +2026-07-16 16:20:10 | INFO | pid=23172 | COMMAND_STARTED command=input input=data\documents\化肥买卖合同　GF—2000—0102.pdf device=cpu log=D:\Dev\ocr-VL1.6\logs\input\化肥买卖合同_GF_2000_0102-cpu-20260716-162010.log +2026-07-16 16:20:10 | INFO | pid=23172 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf kind=pdf mode=hybrid +2026-07-16 16:20:10 | INFO | pid=23172 | PDF_PREFLIGHT_COMPLETED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf page_count=2 selected_pages=2 output=D:\Dev\ocr-VL1.6\outputs\pdfs\化肥买卖合同_GF_2000_0102 mode=hybrid +2026-07-16 16:20:10 | INFO | pid=23172 | PDF_OPENED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf mode=hybrid seconds=0.001 dpi=144 +2026-07-16 16:20:10 | INFO | pid=23172 | TASK_PLAN mode=hybrid total_pages=2 selected_pages=2 completed_before=0 pending_pages=2 +2026-07-16 16:20:10 | INFO | pid=23172 | PAGE_START page=1 position=1/2 mode=hybrid +2026-07-16 16:20:10 | INFO | pid=23172 | PAGE_ROUTED page=1 source=text reason=usable_text_layer text_chars=251 printable_ratio=1.0000 content_ratio=0.8566 density=500.841 text_extract_seconds=0.008 +2026-07-16 16:20:10 | INFO | pid=23172 | PAGE_FINISHED page=1 status=completed source=text text_extract_seconds=0.008 render_seconds=0.000 ocr_seconds=0.000 export_seconds=0.003 state_save_seconds=0.028 total_seconds=0.012 eta_seconds=0.012 progress=1/2 +2026-07-16 16:20:10 | INFO | pid=23172 | PAGE_START page=2 position=2/2 mode=hybrid +2026-07-16 16:20:10 | INFO | pid=23172 | PAGE_ROUTED page=2 source=text reason=usable_text_layer text_chars=371 printable_ratio=1.0000 content_ratio=0.8194 density=740.287 text_extract_seconds=0.002 +2026-07-16 16:20:10 | INFO | pid=23172 | PAGE_FINISHED page=2 status=completed source=text text_extract_seconds=0.002 render_seconds=0.000 ocr_seconds=0.000 export_seconds=0.002 state_save_seconds=0.003 total_seconds=0.004 eta_seconds=0.000 progress=2/2 +2026-07-16 16:20:10 | INFO | pid=23172 | TASK_COMPLETED status=completed mode=hybrid selected_pages=2 text_pages=2 ocr_pages=0 failed_pages=[] model_used=False model_initialized_during_task=False model_available=False model_init_seconds=0.000 text_extract_total_seconds=0.010 render_total_seconds=0.000 ocr_total_seconds=0.000 task_total_seconds=0.056 +2026-07-16 16:20:10 | INFO | pid=23172 | PDF_COMPLETED path=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf status=completed text_pages=2 ocr_pages=0 failed_pages=[] model_used=False model_initialized_during_task=False resume=False file_total_seconds=0.063 output=D:\Dev\ocr-VL1.6\outputs\pdfs\化肥买卖合同_GF_2000_0102 +2026-07-16 16:20:10 | INFO | pid=23172 | PROGRAM_COMPLETED input=D:\Dev\ocr-VL1.6\data\documents\化肥买卖合同　GF—2000—0102.pdf kind=pdf status=completed file_seconds=0.063 program_total_seconds=0.063 diff --git a/logs/input/合同01-cpu-20260716-163937.log b/logs/input/合同01-cpu-20260716-163937.log new file mode 100644 index 0000000..8704aee --- /dev/null +++ b/logs/input/合同01-cpu-20260716-163937.log @@ -0,0 +1,33 @@ +2026-07-16 16:39:37 | INFO | pid=12156 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\合同01-cpu-20260716-163937.log +2026-07-16 16:39:37 | INFO | pid=12156 | COMMAND_STARTED command=input input=data\images\合同01.jpg device=cpu log=D:\Dev\ocr-VL1.6\logs\input\合同01-cpu-20260716-163937.log +2026-07-16 16:39:37 | INFO | pid=12156 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg kind=image +2026-07-16 16:39:37 | INFO | pid=12156 | CPU_CONFIGURED threads=18 total_cores=20 reserved_cores=2 +2026-07-16 16:39:37 | INFO | pid=12156 | RUNTIME_PREPARED device=cpu paddle_version=3.2.1 import_seconds=0.757 setup_seconds=0.017 +2026-07-16 16:39:37 | INFO | pid=12156 | MODEL_INITIALIZATION_STARTED pipeline_version=v1.6 device=cpu +2026-07-16 16:40:16 | INFO | pid=12156 | MODEL_INITIALIZED seconds=39.070 device=cpu +2026-07-16 16:46:20 | INFO | pid=12156 | INFERENCE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg round=1/1 seconds=363.868 +2026-07-16 16:46:20 | INFO | pid=12156 | IMAGE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg width=768 height=1024 layout_boxes=24 parsed_blocks=23 inference_mean_seconds=363.868 export_seconds=0.017 file_total_seconds=403.892 output=D:\Dev\ocr-VL1.6\outputs\images\合同01_jpg benchmark=D:\Dev\ocr-VL1.6\outputs\images\合同01_jpg\benchmark.json +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=1 label=doc_title bbox=[312, 57, 454, 82] content=购销合同 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=2 label=text bbox=[52, 91, 233, 106] content=合同编号：QYXX-20250418008 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=3 label=text bbox=[51, 109, 713, 149] content=本合同根据《中华人民共和国民法典》、《中华人民共和国产品质量法》与本合同交易相关其它有关法律法规制定。经友好协商，甲乙双方一致同意按照下列条款签订本合同达成合同如下： +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=4 label=text bbox=[52, 148, 333, 163] content=产品名称、规格型号、产品品牌、数量、价格： +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=5 label=table bbox=[46, 165, 721, 243] content=
品牌与名称规格/型号数量单位单价（元）合计（元）货期
KELLER222308.0308 PR-23SY / 2,5bar / 81549.331个103010306-8 周
大写（人民币）： 壹仟零叁拾圆整 含税含运费（13%专票）总价： 1030.00
+2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=6 label=text bbox=[54, 246, 206, 260] content=二、质量要求、随货资料 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=7 label=text bbox=[51, 264, 714, 300] content=1. 符合原厂标准，同时符合国家相关标准及行业规定，标准不一致情况下应符合其最高者。100%全新未拆封原装原厂正品，随货提供原产地证明，海关报关单，产品合格证书，产品质量检测报告等附件.假一赔三质保2年 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=8 label=paragraph_title bbox=[53, 303, 206, 318] content=三、交货地点、包装运输 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=9 label=text bbox=[53, 322, 126, 337] content=1. 交货地点： +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=10 label=text bbox=[51, 339, 642, 355] content=2. 乙方应使用适当运输和搬运的包装并采取必要的保护措施，确保合同货物安全到达甲方指定现场。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=11 label=text bbox=[52, 359, 480, 374] content=3. 运费及保险费由乙方承担，货交甲方之前的毁损灭失风险由乙方承担。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=12 label=text bbox=[53, 378, 151, 393] content=四、付款、发票 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=13 label=text bbox=[53, 397, 262, 412] content=1 付款方式：银行转账。全款付清。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=14 label=text bbox=[54, 417, 152, 430] content=五、验收、凭证 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=15 label=text bbox=[51, 435, 714, 469] content=1. 货物抵达目的地后，甲方对货物进行检验。如发现货物的规格、数量、质量与合同规定不符，甲方可以选择换货或退货，且由此给甲方造成的所有损失都由乙方进行赔偿。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=16 label=text bbox=[51, 473, 714, 507] content=2. 货物抵达现场后，乙方应提供与实际数量相符的发货清单，并经甲方收货人员确认签字后方可生效，生效后发货清单将作为最终结算的凭证。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=17 label=paragraph_title bbox=[53, 512, 138, 526] content=六、违约责任 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=18 label=text bbox=[51, 530, 714, 564] content=1. 合同生效后，除经双方友好协商且有书面协议外，任何一方都不得擅自解除本合同，若任何一方擅自解除本合同的，向另一方支付合同总价5%的违约金。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=19 label=text bbox=[51, 569, 714, 622] content=2. 若乙方不能按合同规定的时间交付货物，每逾期一天，乙方向甲方支付合同总价的0.5%的违约金，违约金总额不超过合同总金额的30%。一旦违约事件发生，乙方需在收到甲方索赔通知书30天内，将违约金电汇给甲方，或者甲方有权书面通知乙方后将违约金直接从合同款中扣除。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=20 label=text bbox=[53, 625, 192, 639] content=七、解决合同纠纷方式 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=21 label=text bbox=[53, 644, 713, 677] content=双方因执行本合同发生的或者与本合同有关的一切争议，经友好协商解决不了的，双方可向仲裁机构申请仲裁或向甲乙方所在地人民法院提起诉讼，仲裁费用由败诉方承担。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=22 label=text bbox=[51, 682, 712, 735] content=八、免责条款：遇不可抗拒因素造成交期延迟或不能交货的，乙方必须及时通知甲方并提供相关的证明资料。\n\n九、合同成立，本合同一式贰份，双方各执一份，具同等法律效力，自双方签字盖章汇款之日起生效（传真件、复印件和原件具有同等法律效力）。 +2026-07-16 16:46:20 | INFO | pid=12156 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\合同01.jpg index=23 label=table bbox=[32, 737, 729, 882] content=
甲方：无锡科卫泰机电设备有限公司乙方：上海奇悦信息科53 室
地址：江阴市顾山镇锡张路 200 号-2 幢 5 楼 A018地址：上海市闵行区元Image
税号：91320281MAEGM8QH37税号：9131011257917:
开户行： 中国农业银行股份有限公司无锡梅村支行开户行：中国银行上海
账号：10653201040026399账号：455959776830
经办人：顾经理经办人：陈柄竹
电话：13701767090电话：17629565182
+2026-07-16 16:46:20 | INFO | pid=12156 | PROGRAM_COMPLETED input=D:\Dev\ocr-VL1.6\data\images\合同01.jpg kind=image status=completed file_seconds=403.892 program_total_seconds=403.896 diff --git a/logs/input/名片02-cpu-20260716-161641.log b/logs/input/名片02-cpu-20260716-161641.log new file mode 100644 index 0000000..18527f7 --- /dev/null +++ b/logs/input/名片02-cpu-20260716-161641.log @@ -0,0 +1,16 @@ +2026-07-16 16:16:41 | INFO | pid=32364 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\名片02-cpu-20260716-161641.log +2026-07-16 16:16:41 | INFO | pid=32364 | COMMAND_STARTED command=input input=data\images\名片02.jpg device=cpu log=D:\Dev\ocr-VL1.6\logs\input\名片02-cpu-20260716-161641.log +2026-07-16 16:16:41 | INFO | pid=32364 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg kind=image +2026-07-16 16:16:41 | INFO | pid=32364 | CPU_CONFIGURED threads=18 total_cores=20 reserved_cores=2 +2026-07-16 16:16:41 | INFO | pid=32364 | RUNTIME_PREPARED device=cpu paddle_version=3.2.1 import_seconds=0.747 setup_seconds=0.015 +2026-07-16 16:16:41 | INFO | pid=32364 | MODEL_INITIALIZATION_STARTED pipeline_version=v1.6 device=cpu +2026-07-16 16:17:21 | INFO | pid=32364 | MODEL_INITIALIZED seconds=39.155 device=cpu +2026-07-16 16:18:37 | INFO | pid=32364 | INFERENCE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg round=1/1 seconds=75.946 +2026-07-16 16:18:37 | INFO | pid=32364 | IMAGE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg width=1440 height=864 layout_boxes=6 parsed_blocks=6 inference_mean_seconds=75.946 export_seconds=0.006 file_total_seconds=115.917 output=D:\Dev\ocr-VL1.6\outputs\images\名片02_jpg benchmark=D:\Dev\ocr-VL1.6\outputs\images\名片02_jpg\benchmark.json +2026-07-16 16:18:37 | INFO | pid=32364 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg index=1 label=paragraph_title bbox=[87, 59, 333, 130] content=白滑影 +2026-07-16 16:18:37 | INFO | pid=32364 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg index=2 label=paragraph_title bbox=[713, 176, 1006, 300] content=姜美丽\n13388866888 +2026-07-16 16:18:37 | INFO | pid=32364 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg index=3 label=paragraph_title bbox=[312, 423, 655, 720] content=夏佳人 +2026-07-16 16:18:37 | INFO | pid=32364 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg index=4 label=paragraph_title bbox=[710, 494, 1346, 563] content=女子时尚瘦身健美馆 +2026-07-16 16:18:37 | INFO | pid=32364 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg index=5 label=text bbox=[713, 572, 1342, 615] content=地址：上海市湘江大街88号滨江大厦 +2026-07-16 16:18:37 | INFO | pid=32364 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\名片02.jpg index=6 label=text bbox=[714, 619, 1208, 660] content=电话：83566666 83588888 +2026-07-16 16:18:37 | INFO | pid=32364 | PROGRAM_COMPLETED input=D:\Dev\ocr-VL1.6\data\images\名片02.jpg kind=image status=completed file_seconds=115.917 program_total_seconds=115.919 diff --git a/logs/input/手写01-cpu-20260716-154552.log b/logs/input/手写01-cpu-20260716-154552.log new file mode 100644 index 0000000..acf495c --- /dev/null +++ b/logs/input/手写01-cpu-20260716-154552.log @@ -0,0 +1,13 @@ +2026-07-16 15:45:52 | INFO | pid=20888 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\手写01-cpu-20260716-154552.log +2026-07-16 15:45:52 | INFO | pid=20888 | COMMAND_STARTED command=input input=data\images\手写01.png device=cpu log=D:\Dev\ocr-VL1.6\logs\input\手写01-cpu-20260716-154552.log +2026-07-16 15:45:52 | INFO | pid=20888 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\images\手写01.png kind=image +2026-07-16 15:45:53 | INFO | pid=20888 | CPU_CONFIGURED threads=18 total_cores=20 reserved_cores=2 +2026-07-16 15:45:53 | INFO | pid=20888 | RUNTIME_PREPARED device=cpu paddle_version=3.2.1 import_seconds=0.760 setup_seconds=0.019 +2026-07-16 15:45:53 | INFO | pid=20888 | MODEL_INITIALIZATION_STARTED pipeline_version=v1.6 device=cpu +2026-07-16 15:46:52 | INFO | pid=20888 | MODEL_INITIALIZED seconds=58.882 device=cpu +2026-07-16 15:49:29 | INFO | pid=20888 | INFERENCE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\手写01.png round=1/1 seconds=157.208 +2026-07-16 15:49:29 | INFO | pid=20888 | IMAGE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\手写01.png width=1758 height=646 layout_boxes=7 parsed_blocks=3 inference_mean_seconds=157.208 file_total_seconds=216.870 benchmark=D:\Dev\ocr-VL1.6\benchmarks\cpu\image-手写01-20260716-154929-745496.json +2026-07-16 15:49:29 | INFO | pid=20888 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=1 label=text bbox=[15, 1, 1027, 289] content=最优质的草场。但是这两年由于旱獭和草原黄鼠的逐年\n保护,人们的行为需要矫正。\n部分。末日的时刻。\n佛巴林卡塔尔等海 +2026-07-16 15:49:29 | INFO | pid=20888 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=2 label=text bbox=[1113, 0, 1697, 254] content= +2026-07-16 15:49:29 | INFO | pid=20888 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=3 label=text bbox=[18, 327, 1758, 640] content=很多消费者没有认识到医学验光的重要性,导致诸多后果。\n特许商品的销售便逐渐升温。文化软实力作出重要贡献。 +2026-07-16 15:49:29 | INFO | pid=20888 | PROGRAM_COMPLETED input=D:\Dev\ocr-VL1.6\data\images\手写01.png kind=image status=completed file_seconds=216.870 program_total_seconds=216.951 diff --git a/logs/input/手写01-cpu-20260716-155113.log b/logs/input/手写01-cpu-20260716-155113.log new file mode 100644 index 0000000..73e824f --- /dev/null +++ b/logs/input/手写01-cpu-20260716-155113.log @@ -0,0 +1,13 @@ +2026-07-16 15:51:13 | INFO | pid=7012 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\手写01-cpu-20260716-155113.log +2026-07-16 15:51:13 | INFO | pid=7012 | COMMAND_STARTED command=input input=data\images\手写01.png device=cpu log=D:\Dev\ocr-VL1.6\logs\input\手写01-cpu-20260716-155113.log +2026-07-16 15:51:13 | INFO | pid=7012 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\images\手写01.png kind=image +2026-07-16 15:51:14 | INFO | pid=7012 | CPU_CONFIGURED threads=18 total_cores=20 reserved_cores=2 +2026-07-16 15:51:14 | INFO | pid=7012 | RUNTIME_PREPARED device=cpu paddle_version=3.2.1 import_seconds=0.740 setup_seconds=0.021 +2026-07-16 15:51:14 | INFO | pid=7012 | MODEL_INITIALIZATION_STARTED pipeline_version=v1.6 device=cpu +2026-07-16 15:52:04 | INFO | pid=7012 | MODEL_INITIALIZED seconds=50.116 device=cpu +2026-07-16 15:54:40 | INFO | pid=7012 | INFERENCE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\手写01.png round=1/1 seconds=155.285 +2026-07-16 15:54:40 | INFO | pid=7012 | IMAGE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\手写01.png width=1758 height=646 layout_boxes=7 parsed_blocks=3 inference_mean_seconds=155.285 file_total_seconds=206.164 benchmark=D:\Dev\ocr-VL1.6\benchmarks\cpu\image-手写01-20260716-155440-158194.json +2026-07-16 15:54:40 | INFO | pid=7012 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=1 label=text bbox=[15, 1, 1027, 289] content=最优质的草场。但是这两年由于旱獭和草原黄鼠的逐年\n保护,人们的行为需要矫正。\n部分。末日的时刻。\n佛巴林卡塔尔等海 +2026-07-16 15:54:40 | INFO | pid=7012 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=2 label=text bbox=[1113, 0, 1697, 254] content= +2026-07-16 15:54:40 | INFO | pid=7012 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=3 label=text bbox=[18, 327, 1758, 640] content=很多消费者没有认识到医学验光的重要性,导致诸多后果。\n特许商品的销售便逐渐升温。文化软实力作出重要贡献。 +2026-07-16 15:54:40 | INFO | pid=7012 | PROGRAM_COMPLETED input=D:\Dev\ocr-VL1.6\data\images\手写01.png kind=image status=completed file_seconds=206.164 program_total_seconds=206.219 diff --git a/logs/input/手写01-cpu-20260716-161232.log b/logs/input/手写01-cpu-20260716-161232.log new file mode 100644 index 0000000..621076e --- /dev/null +++ b/logs/input/手写01-cpu-20260716-161232.log @@ -0,0 +1,13 @@ +2026-07-16 16:12:32 | INFO | pid=10552 | LOG_INITIALIZED file=D:\Dev\ocr-VL1.6\logs\input\手写01-cpu-20260716-161232.log +2026-07-16 16:12:32 | INFO | pid=10552 | COMMAND_STARTED command=input input=data\images\手写01.png device=cpu log=D:\Dev\ocr-VL1.6\logs\input\手写01-cpu-20260716-161232.log +2026-07-16 16:12:32 | INFO | pid=10552 | FILE_ROUTED path=D:\Dev\ocr-VL1.6\data\images\手写01.png kind=image +2026-07-16 16:12:33 | INFO | pid=10552 | CPU_CONFIGURED threads=18 total_cores=20 reserved_cores=2 +2026-07-16 16:12:33 | INFO | pid=10552 | RUNTIME_PREPARED device=cpu paddle_version=3.2.1 import_seconds=0.790 setup_seconds=0.024 +2026-07-16 16:12:33 | INFO | pid=10552 | MODEL_INITIALIZATION_STARTED pipeline_version=v1.6 device=cpu +2026-07-16 16:13:12 | INFO | pid=10552 | MODEL_INITIALIZED seconds=38.981 device=cpu +2026-07-16 16:15:48 | INFO | pid=10552 | INFERENCE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\手写01.png round=1/1 seconds=155.926 +2026-07-16 16:15:48 | INFO | pid=10552 | IMAGE_COMPLETED path=D:\Dev\ocr-VL1.6\data\images\手写01.png width=1758 height=646 layout_boxes=7 parsed_blocks=3 inference_mean_seconds=155.926 export_seconds=0.006 file_total_seconds=195.801 output=D:\Dev\ocr-VL1.6\outputs\images\手写01_png benchmark=D:\Dev\ocr-VL1.6\outputs\images\手写01_png\benchmark.json +2026-07-16 16:15:48 | INFO | pid=10552 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=1 label=text bbox=[15, 1, 1027, 289] content=最优质的草场。但是这两年由于旱獭和草原黄鼠的逐年\n保护,人们的行为需要矫正。\n部分。末日的时刻。\n佛巴林卡塔尔等海 +2026-07-16 16:15:48 | INFO | pid=10552 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=2 label=text bbox=[1113, 0, 1697, 254] content= +2026-07-16 16:15:48 | INFO | pid=10552 | OCR_BLOCK path=D:\Dev\ocr-VL1.6\data\images\手写01.png index=3 label=text bbox=[18, 327, 1758, 640] content=很多消费者没有认识到医学验光的重要性,导致诸多后果。\n特许商品的销售便逐渐升温。文化软实力作出重要贡献。 +2026-07-16 16:15:48 | INFO | pid=10552 | PROGRAM_COMPLETED input=D:\Dev\ocr-VL1.6\data\images\手写01.png kind=image status=completed file_seconds=195.801 program_total_seconds=195.803 diff --git a/outputs/images/合同01_jpg/assets/001-img_in_seal_box_534_741_674_880.jpg b/outputs/images/合同01_jpg/assets/001-img_in_seal_box_534_741_674_880.jpg new file mode 100644 index 0000000..192f404 Binary files /dev/null and b/outputs/images/合同01_jpg/assets/001-img_in_seal_box_534_741_674_880.jpg differ diff --git a/outputs/images/合同01_jpg/benchmark.json b/outputs/images/合同01_jpg/benchmark.json new file mode 100644 index 0000000..790a9b4 --- /dev/null +++ b/outputs/images/合同01_jpg/benchmark.json @@ -0,0 +1,41 @@ +{ + "timestamp": "2026-07-16T16:46:20.795128+08:00", + "device": "cpu", + "device_name": "Intel64 Family 6 Model 151 Stepping 2, GenuineIntel", + "cpu_threads": 18, + "python_version": "3.13.13", + "platform": "Windows-11-10.0.26200-SP0", + "paddle_version": "3.2.1", + "pipeline_version": "v1.6", + "runtime_import_seconds": 0.757, + "runtime_setup_seconds": 0.017, + "model_init_seconds": 39.07, + "image_path": "D:\\Dev\\ocr-VL1.6\\data\\images\\合同01.jpg", + "image": { + "width": 768, + "height": 1024, + "layout_boxes": 24, + "parsed_blocks": 23, + "non_empty_blocks": 23 + }, + "warmup_seconds": [], + "inference_seconds": { + "all": [ + 363.868 + ], + "min": 363.868, + "max": 363.868, + "mean": 363.868, + "median": 363.868, + "stdev": 0.0 + }, + "gpu_memory": { + "allocated_mb": null, + "reserved_mb": null, + "max_allocated_mb": null, + "max_reserved_mb": null + }, + "processing_seconds": 403.714, + "export_seconds": 0.017, + "file_total_seconds": 403.892 +} \ No newline at end of file diff --git a/outputs/images/合同01_jpg/result.json b/outputs/images/合同01_jpg/result.json new file mode 100644 index 0000000..0e2ccbc --- /dev/null +++ b/outputs/images/合同01_jpg/result.json @@ -0,0 +1,1470 @@ +{ + "res": { + "input_path": "D:\\Dev\\ocr-VL1.6\\data\\images\\合同01.jpg", + "page_index": null, + "page_count": null, + "width": 768, + "height": 1024, + "model_settings": { + "use_doc_preprocessor": false, + "use_layout_detection": true, + "use_chart_recognition": false, + "use_seal_recognition": false, + "use_ocr_for_image_block": false, + "format_block_content": false, + "merge_layout_blocks": true, + "markdown_ignore_labels": [ + "number", + "footnote", + "header", + "header_image", + "footer", + "footer_image", + "aside_text" + ], + "return_layout_polygon_points": true + }, + "parsing_res_list": [ + { + "block_label": "doc_title", + "block_content": "购销合同", + "block_bbox": [ + 312, + 57, + 454, + 82 + ], + "block_id": 0, + "block_order": 1, + "group_id": 0, + "block_polygon_points": [ + [ + 312.0, + 57.0 + ], + [ + 454.0, + 57.0 + ], + [ + 454.0, + 82.0 + ], + [ + 312.0, + 82.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "合同编号：QYXX-20250418008", + "block_bbox": [ + 52, + 91, + 233, + 106 + ], + "block_id": 1, + "block_order": 2, + "group_id": 1, + "block_polygon_points": [ + [ + 52.0, + 91.0 + ], + [ + 232.0, + 91.0 + ], + [ + 232.0, + 105.0 + ], + [ + 52.0, + 105.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "本合同根据《中华人民共和国民法典》、《中华人民共和国产品质量法》与本合同交易相关其它有关法律法规制定。经友好协商，甲乙双方一致同意按照下列条款签订本合同达成合同如下：", + "block_bbox": [ + 51, + 109, + 713, + 149 + ], + "block_id": 2, + "block_order": 3, + "group_id": 2, + "block_polygon_points": [ + [ + 51.0, + 109.0 + ], + [ + 713.0, + 109.0 + ], + [ + 713.0, + 149.0 + ], + [ + 51.0, + 149.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "产品名称、规格型号、产品品牌、数量、价格：", + "block_bbox": [ + 52, + 148, + 333, + 163 + ], + "block_id": 3, + "block_order": 4, + "group_id": 3, + "block_polygon_points": [ + [ + 52.0, + 148.0 + ], + [ + 52.0, + 162.0 + ], + [ + 332.0, + 162.0 + ], + [ + 332.0, + 148.0 + ] + ] + }, + { + "block_label": "table", + "block_content": "
品牌与名称规格/型号数量单位单价（元）合计（元）货期
KELLER222308.0308 PR-23SY / 2,5bar / 81549.331个103010306-8 周
大写（人民币）： 壹仟零叁拾圆整 含税含运费（13%专票）总价： 1030.00
", + "block_bbox": [ + 46, + 165, + 721, + 243 + ], + "block_id": 4, + "block_order": null, + "group_id": 4, + "block_polygon_points": [ + [ + 46.0, + 165.0 + ], + [ + 721.0, + 165.0 + ], + [ + 721.0, + 243.0 + ], + [ + 46.0, + 243.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "二、质量要求、随货资料", + "block_bbox": [ + 54, + 246, + 206, + 260 + ], + "block_id": 5, + "block_order": 5, + "group_id": 5, + "block_polygon_points": [ + [ + 54.0, + 246.0 + ], + [ + 205.0, + 246.0 + ], + [ + 205.0, + 259.0 + ], + [ + 54.0, + 259.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "1. 符合原厂标准，同时符合国家相关标准及行业规定，标准不一致情况下应符合其最高者。100%全新未拆封原装原厂正品，随货提供原产地证明，海关报关单，产品合格证书，产品质量检测报告等附件.假一赔三质保2年", + "block_bbox": [ + 51, + 264, + 714, + 300 + ], + "block_id": 6, + "block_order": 6, + "group_id": 6, + "block_polygon_points": [ + [ + 51.0, + 264.0 + ], + [ + 714.0, + 264.0 + ], + [ + 714.0, + 300.0 + ], + [ + 51.0, + 300.0 + ] + ] + }, + { + "block_label": "paragraph_title", + "block_content": "三、交货地点、包装运输", + "block_bbox": [ + 53, + 303, + 206, + 318 + ], + "block_id": 7, + "block_order": 7, + "group_id": 7, + "block_polygon_points": [ + [ + 53.0, + 303.0 + ], + [ + 205.0, + 303.0 + ], + [ + 205.0, + 317.0 + ], + [ + 53.0, + 317.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "1. 交货地点：", + "block_bbox": [ + 53, + 322, + 126, + 337 + ], + "block_id": 8, + "block_order": 8, + "group_id": 8, + "block_polygon_points": [ + [ + 53.0, + 322.0 + ], + [ + 125.0, + 322.0 + ], + [ + 125.0, + 336.0 + ], + [ + 53.0, + 336.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "2. 乙方应使用适当运输和搬运的包装并采取必要的保护措施，确保合同货物安全到达甲方指定现场。", + "block_bbox": [ + 51, + 339, + 642, + 355 + ], + "block_id": 9, + "block_order": 9, + "group_id": 9, + "block_polygon_points": [ + [ + 55.0, + 338.9999694824219 + ], + [ + 640.9998779296875, + 338.9999694824219 + ], + [ + 640.9998779296875, + 353.9999694824219 + ], + [ + 55.0, + 353.9999694824219 + ] + ] + }, + { + "block_label": "text", + "block_content": "3. 运费及保险费由乙方承担，货交甲方之前的毁损灭失风险由乙方承担。", + "block_bbox": [ + 52, + 359, + 480, + 374 + ], + "block_id": 10, + "block_order": 10, + "group_id": 10, + "block_polygon_points": [ + [ + 52.0, + 358.9999694824219 + ], + [ + 478.99993896484375, + 358.9999694824219 + ], + [ + 478.99993896484375, + 372.9999694824219 + ], + [ + 52.0, + 372.9999694824219 + ] + ] + }, + { + "block_label": "text", + "block_content": "四、付款、发票", + "block_bbox": [ + 53, + 378, + 151, + 393 + ], + "block_id": 11, + "block_order": 11, + "group_id": 11, + "block_polygon_points": [ + [ + 53.0, + 377.9999694824219 + ], + [ + 149.99998474121094, + 377.9999694824219 + ], + [ + 149.99998474121094, + 391.9999694824219 + ], + [ + 53.0, + 391.9999694824219 + ] + ] + }, + { + "block_label": "text", + "block_content": "1 付款方式：银行转账。全款付清。", + "block_bbox": [ + 53, + 397, + 262, + 412 + ], + "block_id": 12, + "block_order": 12, + "group_id": 12, + "block_polygon_points": [ + [ + 53.0, + 397.0 + ], + [ + 261.0, + 397.0 + ], + [ + 261.0, + 411.0 + ], + [ + 53.0, + 411.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "五、验收、凭证", + "block_bbox": [ + 54, + 417, + 152, + 430 + ], + "block_id": 13, + "block_order": 13, + "group_id": 13, + "block_polygon_points": [ + [ + 54.0, + 417.0 + ], + [ + 150.99998474121094, + 417.0 + ], + [ + 150.99998474121094, + 429.0 + ], + [ + 54.0, + 429.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "1. 货物抵达目的地后，甲方对货物进行检验。如发现货物的规格、数量、质量与合同规定不符，甲方可以选择换货或退货，且由此给甲方造成的所有损失都由乙方进行赔偿。", + "block_bbox": [ + 51, + 435, + 714, + 469 + ], + "block_id": 14, + "block_order": 14, + "group_id": 14, + "block_polygon_points": [ + [ + 51.0, + 435.0 + ], + [ + 714.0, + 435.0 + ], + [ + 714.0, + 469.0 + ], + [ + 51.0, + 469.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "2. 货物抵达现场后，乙方应提供与实际数量相符的发货清单，并经甲方收货人员确认签字后方可生效，生效后发货清单将作为最终结算的凭证。", + "block_bbox": [ + 51, + 473, + 714, + 507 + ], + "block_id": 15, + "block_order": 15, + "group_id": 15, + "block_polygon_points": [ + [ + 51.0, + 473.0 + ], + [ + 714.0, + 473.0 + ], + [ + 714.0, + 507.0 + ], + [ + 51.0, + 507.0 + ] + ] + }, + { + "block_label": "paragraph_title", + "block_content": "六、违约责任", + "block_bbox": [ + 53, + 512, + 138, + 526 + ], + "block_id": 16, + "block_order": 16, + "group_id": 16, + "block_polygon_points": [ + [ + 53.0, + 512.0 + ], + [ + 137.0, + 512.0 + ], + [ + 137.0, + 525.0 + ], + [ + 53.0, + 525.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "1. 合同生效后，除经双方友好协商且有书面协议外，任何一方都不得擅自解除本合同，若任何一方擅自解除本合同的，向另一方支付合同总价5%的违约金。", + "block_bbox": [ + 51, + 530, + 714, + 564 + ], + "block_id": 17, + "block_order": 17, + "group_id": 17, + "block_polygon_points": [ + [ + 51.0, + 530.0 + ], + [ + 714.0, + 530.0 + ], + [ + 714.0, + 564.0 + ], + [ + 51.0, + 564.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "2. 若乙方不能按合同规定的时间交付货物，每逾期一天，乙方向甲方支付合同总价的0.5%的违约金，违约金总额不超过合同总金额的30%。一旦违约事件发生，乙方需在收到甲方索赔通知书30天内，将违约金电汇给甲方，或者甲方有权书面通知乙方后将违约金直接从合同款中扣除。", + "block_bbox": [ + 51, + 569, + 714, + 622 + ], + "block_id": 18, + "block_order": 18, + "group_id": 18, + "block_polygon_points": [ + [ + 51.0, + 569.0 + ], + [ + 714.0, + 569.0 + ], + [ + 714.0, + 622.0 + ], + [ + 51.0, + 622.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "七、解决合同纠纷方式", + "block_bbox": [ + 53, + 625, + 192, + 639 + ], + "block_id": 19, + "block_order": 19, + "group_id": 19, + "block_polygon_points": [ + [ + 53.0, + 625.0 + ], + [ + 191.0, + 625.0 + ], + [ + 191.0, + 638.0 + ], + [ + 53.0, + 638.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "双方因执行本合同发生的或者与本合同有关的一切争议，经友好协商解决不了的，双方可向仲裁机构申请仲裁或向甲乙方所在地人民法院提起诉讼，仲裁费用由败诉方承担。", + "block_bbox": [ + 53, + 644, + 713, + 677 + ], + "block_id": 20, + "block_order": 20, + "group_id": 20, + "block_polygon_points": [ + [ + 53.0, + 644.0 + ], + [ + 713.0, + 644.0 + ], + [ + 713.0, + 677.0 + ], + [ + 53.0, + 677.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "八、免责条款：遇不可抗拒因素造成交期延迟或不能交货的，乙方必须及时通知甲方并提供相关的证明资料。\n\n九、合同成立，本合同一式贰份，双方各执一份，具同等法律效力，自双方签字盖章汇款之日起生效（传真件、复印件和原件具有同等法律效力）。", + "block_bbox": [ + 51, + 682, + 712, + 735 + ], + "block_id": 21, + "block_order": 21, + "group_id": 21, + "block_polygon_points": [ + [ + 51.0, + 682.0 + ], + [ + 712.0, + 682.0 + ], + [ + 712.0, + 735.0 + ], + [ + 51.0, + 735.0 + ] + ] + }, + { + "block_label": "table", + "block_content": "
甲方：无锡科卫泰机电设备有限公司乙方：上海奇悦信息科53 室
地址：江阴市顾山镇锡张路 200 号-2 幢 5 楼 A018地址：上海市闵行区元\"Image\"\"
税号：91320281MAEGM8QH37税号：9131011257917:
开户行： 中国农业银行股份有限公司无锡梅村支行开户行：中国银行上海
账号：10653201040026399账号：455959776830
经办人：顾经理经办人：陈柄竹
电话：13701767090电话：17629565182
", + "block_bbox": [ + 32, + 737, + 729, + 882 + ], + "block_id": 22, + "block_order": null, + "group_id": 22, + "block_polygon_points": [ + [ + 32.0, + 737.0 + ], + [ + 729.0, + 737.0 + ], + [ + 729.0, + 882.0 + ], + [ + 32.0, + 882.0 + ] + ] + } + ], + "layout_det_res": { + "input_path": null, + "page_index": null, + "boxes": [ + { + "cls_id": 6, + "label": "doc_title", + "score": 0.8910382986068726, + "coordinate": [ + 312, + 57, + 454, + 82 + ], + "order": 1, + "polygon_points": [ + [ + 312.0, + 57.0 + ], + [ + 454.0, + 57.0 + ], + [ + 454.0, + 82.0 + ], + [ + 312.0, + 82.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7118394374847412, + "coordinate": [ + 52, + 91, + 233, + 106 + ], + "order": 2, + "polygon_points": [ + [ + 52.0, + 91.0 + ], + [ + 232.0, + 91.0 + ], + [ + 232.0, + 105.0 + ], + [ + 52.0, + 105.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.6959852576255798, + "coordinate": [ + 51, + 109, + 713, + 149 + ], + "order": 3, + "polygon_points": [ + [ + 51.0, + 109.0 + ], + [ + 713.0, + 109.0 + ], + [ + 713.0, + 149.0 + ], + [ + 51.0, + 149.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.4520532786846161, + "coordinate": [ + 52, + 148, + 333, + 163 + ], + "order": 4, + "polygon_points": [ + [ + 52.0, + 148.0 + ], + [ + 52.0, + 162.0 + ], + [ + 332.0, + 162.0 + ], + [ + 332.0, + 148.0 + ] + ] + }, + { + "cls_id": 21, + "label": "table", + "score": 0.9425208568572998, + "coordinate": [ + 46, + 165, + 721, + 243 + ], + "order": null, + "polygon_points": [ + [ + 46.0, + 165.0 + ], + [ + 721.0, + 165.0 + ], + [ + 721.0, + 243.0 + ], + [ + 46.0, + 243.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.5723949670791626, + "coordinate": [ + 54, + 246, + 206, + 260 + ], + "order": 5, + "polygon_points": [ + [ + 54.0, + 246.0 + ], + [ + 205.0, + 246.0 + ], + [ + 205.0, + 259.0 + ], + [ + 54.0, + 259.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7420650720596313, + "coordinate": [ + 51, + 264, + 714, + 300 + ], + "order": 6, + "polygon_points": [ + [ + 51.0, + 264.0 + ], + [ + 714.0, + 264.0 + ], + [ + 714.0, + 300.0 + ], + [ + 51.0, + 300.0 + ] + ] + }, + { + "cls_id": 17, + "label": "paragraph_title", + "score": 0.5606143474578857, + "coordinate": [ + 53, + 303, + 206, + 318 + ], + "order": 7, + "polygon_points": [ + [ + 53.0, + 303.0 + ], + [ + 205.0, + 303.0 + ], + [ + 205.0, + 317.0 + ], + [ + 53.0, + 317.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7677538990974426, + "coordinate": [ + 53, + 322, + 126, + 337 + ], + "order": 8, + "polygon_points": [ + [ + 53.0, + 322.0 + ], + [ + 125.0, + 322.0 + ], + [ + 125.0, + 336.0 + ], + [ + 53.0, + 336.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.8177271485328674, + "coordinate": [ + 51, + 339, + 642, + 355 + ], + "order": 9, + "polygon_points": [ + [ + 55.0, + 338.9999694824219 + ], + [ + 640.9998779296875, + 338.9999694824219 + ], + [ + 640.9998779296875, + 353.9999694824219 + ], + [ + 55.0, + 353.9999694824219 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.8268476724624634, + "coordinate": [ + 52, + 359, + 480, + 374 + ], + "order": 10, + "polygon_points": [ + [ + 52.0, + 358.9999694824219 + ], + [ + 478.99993896484375, + 358.9999694824219 + ], + [ + 478.99993896484375, + 372.9999694824219 + ], + [ + 52.0, + 372.9999694824219 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7748547792434692, + "coordinate": [ + 53, + 378, + 151, + 393 + ], + "order": 11, + "polygon_points": [ + [ + 53.0, + 377.9999694824219 + ], + [ + 149.99998474121094, + 377.9999694824219 + ], + [ + 149.99998474121094, + 391.9999694824219 + ], + [ + 53.0, + 391.9999694824219 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.8143175840377808, + "coordinate": [ + 53, + 397, + 262, + 412 + ], + "order": 12, + "polygon_points": [ + [ + 53.0, + 397.0 + ], + [ + 261.0, + 397.0 + ], + [ + 261.0, + 411.0 + ], + [ + 53.0, + 411.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7891096472740173, + "coordinate": [ + 54, + 417, + 152, + 430 + ], + "order": 13, + "polygon_points": [ + [ + 54.0, + 417.0 + ], + [ + 150.99998474121094, + 417.0 + ], + [ + 150.99998474121094, + 429.0 + ], + [ + 54.0, + 429.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.9224399328231812, + "coordinate": [ + 51, + 435, + 714, + 469 + ], + "order": 14, + "polygon_points": [ + [ + 51.0, + 435.0 + ], + [ + 714.0, + 435.0 + ], + [ + 714.0, + 469.0 + ], + [ + 51.0, + 469.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.8926385045051575, + "coordinate": [ + 51, + 473, + 714, + 507 + ], + "order": 15, + "polygon_points": [ + [ + 51.0, + 473.0 + ], + [ + 714.0, + 473.0 + ], + [ + 714.0, + 507.0 + ], + [ + 51.0, + 507.0 + ] + ] + }, + { + "cls_id": 17, + "label": "paragraph_title", + "score": 0.5336403846740723, + "coordinate": [ + 53, + 512, + 138, + 526 + ], + "order": 16, + "polygon_points": [ + [ + 53.0, + 512.0 + ], + [ + 137.0, + 512.0 + ], + [ + 137.0, + 525.0 + ], + [ + 53.0, + 525.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.9182999134063721, + "coordinate": [ + 51, + 530, + 714, + 564 + ], + "order": 17, + "polygon_points": [ + [ + 51.0, + 530.0 + ], + [ + 714.0, + 530.0 + ], + [ + 714.0, + 564.0 + ], + [ + 51.0, + 564.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.9265676736831665, + "coordinate": [ + 51, + 569, + 714, + 622 + ], + "order": 18, + "polygon_points": [ + [ + 51.0, + 569.0 + ], + [ + 714.0, + 569.0 + ], + [ + 714.0, + 622.0 + ], + [ + 51.0, + 622.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7709159255027771, + "coordinate": [ + 53, + 625, + 192, + 639 + ], + "order": 19, + "polygon_points": [ + [ + 53.0, + 625.0 + ], + [ + 191.0, + 625.0 + ], + [ + 191.0, + 638.0 + ], + [ + 53.0, + 638.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.8900164365768433, + "coordinate": [ + 53, + 644, + 713, + 677 + ], + "order": 20, + "polygon_points": [ + [ + 53.0, + 644.0 + ], + [ + 713.0, + 644.0 + ], + [ + 713.0, + 677.0 + ], + [ + 53.0, + 677.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.9075173139572144, + "coordinate": [ + 51, + 682, + 712, + 735 + ], + "order": 21, + "polygon_points": [ + [ + 51.0, + 682.0 + ], + [ + 712.0, + 682.0 + ], + [ + 712.0, + 735.0 + ], + [ + 51.0, + 735.0 + ] + ] + }, + { + "cls_id": 21, + "label": "table", + "score": 0.9367213845252991, + "coordinate": [ + 32, + 737, + 729, + 882 + ], + "order": null, + "polygon_points": [ + [ + 32.0, + 737.0 + ], + [ + 729.0, + 737.0 + ], + [ + 729.0, + 882.0 + ], + [ + 32.0, + 882.0 + ] + ] + }, + { + "cls_id": 20, + "label": "seal", + "score": 0.935007631778717, + "coordinate": [ + 534, + 741, + 674, + 880 + ], + "order": 22, + "polygon_points": [ + [ + 534.0, + 741.0 + ], + [ + 674.0, + 741.0 + ], + [ + 674.0, + 880.0 + ], + [ + 534.0, + 880.0 + ] + ] + } + ] + }, + "source_type": "image_ocr" + } +} \ No newline at end of file diff --git a/outputs/images/合同01_jpg/result.md b/outputs/images/合同01_jpg/result.md new file mode 100644 index 0000000..295fe99 --- /dev/null +++ b/outputs/images/合同01_jpg/result.md @@ -0,0 +1,49 @@ +# 购销合同 + +合同编号：QYXX-20250418008 + +本合同根据《中华人民共和国民法典》、《中华人民共和国产品质量法》与本合同交易相关其它有关法律法规制定。经友好协商，甲乙双方一致同意按照下列条款签订本合同达成合同如下： + +产品名称、规格型号、产品品牌、数量、价格： + + +
品牌与名称规格/型号数量单位单价（元）合计（元）货期
KELLER222308.0308 PR-23SY / 2,5bar / 81549.331个103010306-8 周
大写（人民币）： 壹仟零叁拾圆整 含税含运费（13%专票）总价： 1030.00
+ +二、质量要求、随货资料 + +1. 符合原厂标准，同时符合国家相关标准及行业规定，标准不一致情况下应符合其最高者。100%全新未拆封原装原厂正品，随货提供原产地证明，海关报关单，产品合格证书，产品质量检测报告等附件.假一赔三质保2年 + +## 三、 交货地点、包装运输 + +1. 交货地点： + +2. 乙方应使用适当运输和搬运的包装并采取必要的保护措施，确保合同货物安全到达甲方指定现场。 + +3. 运费及保险费由乙方承担，货交甲方之前的毁损灭失风险由乙方承担。 + +四、付款、发票 + +1 付款方式：银行转账。全款付清。 + +五、验收、凭证 + +1. 货物抵达目的地后，甲方对货物进行检验。如发现货物的规格、数量、质量与合同规定不符，甲方可以选择换货或退货，且由此给甲方造成的所有损失都由乙方进行赔偿。 + +2. 货物抵达现场后，乙方应提供与实际数量相符的发货清单，并经甲方收货人员确认签字后方可生效，生效后发货清单将作为最终结算的凭证。 + +## 六、 违约责任 + +1. 合同生效后，除经双方友好协商且有书面协议外，任何一方都不得擅自解除本合同，若任何一方擅自解除本合同的，向另一方支付合同总价5%的违约金。 + +2. 若乙方不能按合同规定的时间交付货物，每逾期一天，乙方向甲方支付合同总价的0.5%的违约金，违约金总额不超过合同总金额的30%。一旦违约事件发生，乙方需在收到甲方索赔通知书30天内，将违约金电汇给甲方，或者甲方有权书面通知乙方后将违约金直接从合同款中扣除。 + +七、解决合同纠纷方式 + +双方因执行本合同发生的或者与本合同有关的一切争议，经友好协商解决不了的，双方可向仲裁机构申请仲裁或向甲乙方所在地人民法院提起诉讼，仲裁费用由败诉方承担。 + +八、免责条款：遇不可抗拒因素造成交期延迟或不能交货的，乙方必须及时通知甲方并提供相关的证明资料。 + +九、合同成立，本合同一式贰份，双方各执一份，具同等法律效力，自双方签字盖章汇款之日起生效（传真件、复印件和原件具有同等法律效力）。 + + +
甲方：无锡科卫泰机电设备有限公司乙方：上海奇悦信息科53 室
地址：江阴市顾山镇锡张路 200 号-2 幢 5 楼 A018地址：上海市闵行区元Image
税号：91320281MAEGM8QH37税号：9131011257917:
开户行： 中国农业银行股份有限公司无锡梅村支行开户行：中国银行上海
账号：10653201040026399账号：455959776830
经办人：顾经理经办人：陈柄竹
电话：13701767090电话：17629565182
diff --git a/outputs/images/合同01_jpg/result.txt b/outputs/images/合同01_jpg/result.txt new file mode 100644 index 0000000..3f182a2 --- /dev/null +++ b/outputs/images/合同01_jpg/result.txt @@ -0,0 +1,47 @@ +购销合同 + +合同编号：QYXX-20250418008 + +本合同根据《中华人民共和国民法典》、《中华人民共和国产品质量法》与本合同交易相关其它有关法律法规制定。经友好协商，甲乙双方一致同意按照下列条款签订本合同达成合同如下： + +产品名称、规格型号、产品品牌、数量、价格： + +
品牌与名称规格/型号数量单位单价（元）合计（元）货期
KELLER222308.0308 PR-23SY / 2,5bar / 81549.331个103010306-8 周
大写（人民币）： 壹仟零叁拾圆整 含税含运费（13%专票）总价： 1030.00
+ +二、质量要求、随货资料 + +1. 符合原厂标准，同时符合国家相关标准及行业规定，标准不一致情况下应符合其最高者。100%全新未拆封原装原厂正品，随货提供原产地证明，海关报关单，产品合格证书，产品质量检测报告等附件.假一赔三质保2年 + +三、交货地点、包装运输 + +1. 交货地点： + +2. 乙方应使用适当运输和搬运的包装并采取必要的保护措施，确保合同货物安全到达甲方指定现场。 + +3. 运费及保险费由乙方承担，货交甲方之前的毁损灭失风险由乙方承担。 + +四、付款、发票 + +1 付款方式：银行转账。全款付清。 + +五、验收、凭证 + +1. 货物抵达目的地后，甲方对货物进行检验。如发现货物的规格、数量、质量与合同规定不符，甲方可以选择换货或退货，且由此给甲方造成的所有损失都由乙方进行赔偿。 + +2. 货物抵达现场后，乙方应提供与实际数量相符的发货清单，并经甲方收货人员确认签字后方可生效，生效后发货清单将作为最终结算的凭证。 + +六、违约责任 + +1. 合同生效后，除经双方友好协商且有书面协议外，任何一方都不得擅自解除本合同，若任何一方擅自解除本合同的，向另一方支付合同总价5%的违约金。 + +2. 若乙方不能按合同规定的时间交付货物，每逾期一天，乙方向甲方支付合同总价的0.5%的违约金，违约金总额不超过合同总金额的30%。一旦违约事件发生，乙方需在收到甲方索赔通知书30天内，将违约金电汇给甲方，或者甲方有权书面通知乙方后将违约金直接从合同款中扣除。 + +七、解决合同纠纷方式 + +双方因执行本合同发生的或者与本合同有关的一切争议，经友好协商解决不了的，双方可向仲裁机构申请仲裁或向甲乙方所在地人民法院提起诉讼，仲裁费用由败诉方承担。 + +八、免责条款：遇不可抗拒因素造成交期延迟或不能交货的，乙方必须及时通知甲方并提供相关的证明资料。 + +九、合同成立，本合同一式贰份，双方各执一份，具同等法律效力，自双方签字盖章汇款之日起生效（传真件、复印件和原件具有同等法律效力）。 + +
甲方：无锡科卫泰机电设备有限公司乙方：上海奇悦信息科53 室
地址：江阴市顾山镇锡张路 200 号-2 幢 5 楼 A018地址：上海市闵行区元Image
税号：91320281MAEGM8QH37税号：9131011257917:
开户行： 中国农业银行股份有限公司无锡梅村支行开户行：中国银行上海
账号：10653201040026399账号：455959776830
经办人：顾经理经办人：陈柄竹
电话：13701767090电话：17629565182
diff --git a/outputs/images/名片02_jpg/benchmark.json b/outputs/images/名片02_jpg/benchmark.json new file mode 100644 index 0000000..cedfbe4 --- /dev/null +++ b/outputs/images/名片02_jpg/benchmark.json @@ -0,0 +1,41 @@ +{ + "timestamp": "2026-07-16T16:18:37.074085+08:00", + "device": "cpu", + "device_name": "Intel64 Family 6 Model 151 Stepping 2, GenuineIntel", + "cpu_threads": 18, + "python_version": "3.13.13", + "platform": "Windows-11-10.0.26200-SP0", + "paddle_version": "3.2.1", + "pipeline_version": "v1.6", + "runtime_import_seconds": 0.747, + "runtime_setup_seconds": 0.015, + "model_init_seconds": 39.155, + "image_path": "D:\\Dev\\ocr-VL1.6\\data\\images\\名片02.jpg", + "image": { + "width": 1440, + "height": 864, + "layout_boxes": 6, + "parsed_blocks": 6, + "non_empty_blocks": 6 + }, + "warmup_seconds": [], + "inference_seconds": { + "all": [ + 75.946 + ], + "min": 75.946, + "max": 75.946, + "mean": 75.946, + "median": 75.946, + "stdev": 0.0 + }, + "gpu_memory": { + "allocated_mb": null, + "reserved_mb": null, + "max_allocated_mb": null, + "max_reserved_mb": null + }, + "processing_seconds": 115.866, + "export_seconds": 0.006, + "file_total_seconds": 115.917 +} \ No newline at end of file diff --git a/outputs/images/名片02_jpg/result.json b/outputs/images/名片02_jpg/result.json new file mode 100644 index 0000000..c22f3c3 --- /dev/null +++ b/outputs/images/名片02_jpg/result.json @@ -0,0 +1,403 @@ +{ + "res": { + "input_path": "D:\\Dev\\ocr-VL1.6\\data\\images\\名片02.jpg", + "page_index": null, + "page_count": null, + "width": 1440, + "height": 864, + "model_settings": { + "use_doc_preprocessor": false, + "use_layout_detection": true, + "use_chart_recognition": false, + "use_seal_recognition": false, + "use_ocr_for_image_block": false, + "format_block_content": false, + "merge_layout_blocks": true, + "markdown_ignore_labels": [ + "number", + "footnote", + "header", + "header_image", + "footer", + "footer_image", + "aside_text" + ], + "return_layout_polygon_points": true + }, + "parsing_res_list": [ + { + "block_label": "paragraph_title", + "block_content": "白滑影", + "block_bbox": [ + 87, + 59, + 333, + 130 + ], + "block_id": 0, + "block_order": 1, + "group_id": 0, + "block_polygon_points": [ + [ + 87.0, + 59.0 + ], + [ + 333.0, + 59.0 + ], + [ + 333.0, + 130.0 + ], + [ + 87.0, + 130.0 + ] + ] + }, + { + "block_label": "paragraph_title", + "block_content": "姜美丽\n13388866888", + "block_bbox": [ + 713, + 176, + 1006, + 300 + ], + "block_id": 1, + "block_order": 2, + "group_id": 1, + "block_polygon_points": [ + [ + 713.0, + 176.0 + ], + [ + 1006.0, + 176.0 + ], + [ + 1006.0, + 300.0 + ], + [ + 713.0, + 300.0 + ] + ] + }, + { + "block_label": "paragraph_title", + "block_content": "夏佳人", + "block_bbox": [ + 312, + 423, + 655, + 720 + ], + "block_id": 2, + "block_order": 3, + "group_id": 2, + "block_polygon_points": [ + [ + 312.0, + 423.0 + ], + [ + 655.0, + 423.0 + ], + [ + 655.0, + 720.0 + ], + [ + 312.0, + 720.0 + ] + ] + }, + { + "block_label": "paragraph_title", + "block_content": "女子时尚瘦身健美馆", + "block_bbox": [ + 710, + 494, + 1346, + 563 + ], + "block_id": 3, + "block_order": 4, + "group_id": 3, + "block_polygon_points": [ + [ + 710.0, + 494.0 + ], + [ + 1346.0, + 494.0 + ], + [ + 1346.0, + 563.0 + ], + [ + 710.0, + 563.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "地址：上海市湘江大街88号滨江大厦", + "block_bbox": [ + 713, + 572, + 1342, + 615 + ], + "block_id": 4, + "block_order": 5, + "group_id": 4, + "block_polygon_points": [ + [ + 713.0, + 572.0 + ], + [ + 1342.0, + 572.0 + ], + [ + 1342.0, + 615.0 + ], + [ + 713.0, + 615.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "电话：83566666 83588888", + "block_bbox": [ + 714, + 619, + 1208, + 660 + ], + "block_id": 5, + "block_order": 6, + "group_id": 5, + "block_polygon_points": [ + [ + 713.676513671875, + 619.1244506835938 + ], + [ + 1206.968505859375, + 615.1220092773438 + ], + [ + 1207.2919921875, + 654.9976196289062 + ], + [ + 714.0, + 659.0000610351562 + ] + ] + } + ], + "layout_det_res": { + "input_path": null, + "page_index": null, + "boxes": [ + { + "cls_id": 17, + "label": "paragraph_title", + "score": 0.49533575773239136, + "coordinate": [ + 87, + 59, + 333, + 130 + ], + "order": 1, + "polygon_points": [ + [ + 87.0, + 59.0 + ], + [ + 333.0, + 59.0 + ], + [ + 333.0, + 130.0 + ], + [ + 87.0, + 130.0 + ] + ] + }, + { + "cls_id": 17, + "label": "paragraph_title", + "score": 0.5912461280822754, + "coordinate": [ + 713, + 176, + 1006, + 300 + ], + "order": 2, + "polygon_points": [ + [ + 713.0, + 176.0 + ], + [ + 1006.0, + 176.0 + ], + [ + 1006.0, + 300.0 + ], + [ + 713.0, + 300.0 + ] + ] + }, + { + "cls_id": 17, + "label": "paragraph_title", + "score": 0.5622609853744507, + "coordinate": [ + 312, + 423, + 655, + 720 + ], + "order": 3, + "polygon_points": [ + [ + 312.0, + 423.0 + ], + [ + 655.0, + 423.0 + ], + [ + 655.0, + 720.0 + ], + [ + 312.0, + 720.0 + ] + ] + }, + { + "cls_id": 17, + "label": "paragraph_title", + "score": 0.7684827446937561, + "coordinate": [ + 710, + 494, + 1346, + 563 + ], + "order": 4, + "polygon_points": [ + [ + 710.0, + 494.0 + ], + [ + 1346.0, + 494.0 + ], + [ + 1346.0, + 563.0 + ], + [ + 710.0, + 563.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7914614677429199, + "coordinate": [ + 713, + 572, + 1342, + 615 + ], + "order": 5, + "polygon_points": [ + [ + 713.0, + 572.0 + ], + [ + 1342.0, + 572.0 + ], + [ + 1342.0, + 615.0 + ], + [ + 713.0, + 615.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.7393481135368347, + "coordinate": [ + 714, + 619, + 1208, + 660 + ], + "order": 6, + "polygon_points": [ + [ + 713.676513671875, + 619.1244506835938 + ], + [ + 1206.968505859375, + 615.1220092773438 + ], + [ + 1207.2919921875, + 654.9976196289062 + ], + [ + 714.0, + 659.0000610351562 + ] + ] + } + ] + }, + "source_type": "image_ocr" + } +} \ No newline at end of file diff --git a/outputs/images/名片02_jpg/result.md b/outputs/images/名片02_jpg/result.md new file mode 100644 index 0000000..b2daf43 --- /dev/null +++ b/outputs/images/名片02_jpg/result.md @@ -0,0 +1,11 @@ +## 白滑影 + +## 姜美丽 13388866888 + +## 夏佳人 + +## 女子时尚瘦身健美馆 + +地址：上海市湘江大街88号滨江大厦 + +电话：83566666 83588888 diff --git a/outputs/images/名片02_jpg/result.txt b/outputs/images/名片02_jpg/result.txt new file mode 100644 index 0000000..2668b2a --- /dev/null +++ b/outputs/images/名片02_jpg/result.txt @@ -0,0 +1,12 @@ +白滑影 + +姜美丽 +13388866888 + +夏佳人 + +女子时尚瘦身健美馆 + +地址：上海市湘江大街88号滨江大厦 + +电话：83566666 83588888 diff --git a/outputs/images/手写01_png/benchmark.json b/outputs/images/手写01_png/benchmark.json new file mode 100644 index 0000000..c0734a2 --- /dev/null +++ b/outputs/images/手写01_png/benchmark.json @@ -0,0 +1,41 @@ +{ + "timestamp": "2026-07-16T16:15:48.316662+08:00", + "device": "cpu", + "device_name": "Intel64 Family 6 Model 151 Stepping 2, GenuineIntel", + "cpu_threads": 18, + "python_version": "3.13.13", + "platform": "Windows-11-10.0.26200-SP0", + "paddle_version": "3.2.1", + "pipeline_version": "v1.6", + "runtime_import_seconds": 0.79, + "runtime_setup_seconds": 0.024, + "model_init_seconds": 38.981, + "image_path": "D:\\Dev\\ocr-VL1.6\\data\\images\\手写01.png", + "image": { + "width": 1758, + "height": 646, + "layout_boxes": 7, + "parsed_blocks": 3, + "non_empty_blocks": 2 + }, + "warmup_seconds": [], + "inference_seconds": { + "all": [ + 155.926 + ], + "min": 155.926, + "max": 155.926, + "mean": 155.926, + "median": 155.926, + "stdev": 0.0 + }, + "gpu_memory": { + "allocated_mb": null, + "reserved_mb": null, + "max_allocated_mb": null, + "max_reserved_mb": null + }, + "processing_seconds": 195.722, + "export_seconds": 0.006, + "file_total_seconds": 195.801 +} \ No newline at end of file diff --git a/outputs/images/手写01_png/result.json b/outputs/images/手写01_png/result.json new file mode 100644 index 0000000..bc187c0 --- /dev/null +++ b/outputs/images/手写01_png/result.json @@ -0,0 +1,364 @@ +{ + "res": { + "input_path": "D:\\Dev\\ocr-VL1.6\\data\\images\\手写01.png", + "page_index": null, + "page_count": null, + "width": 1758, + "height": 646, + "model_settings": { + "use_doc_preprocessor": false, + "use_layout_detection": true, + "use_chart_recognition": false, + "use_seal_recognition": false, + "use_ocr_for_image_block": false, + "format_block_content": false, + "merge_layout_blocks": true, + "markdown_ignore_labels": [ + "number", + "footnote", + "header", + "header_image", + "footer", + "footer_image", + "aside_text" + ], + "return_layout_polygon_points": true + }, + "parsing_res_list": [ + { + "block_label": "text", + "block_content": "最优质的草场。但是这两年由于旱獭和草原黄鼠的逐年\n保护,人们的行为需要矫正。\n部分。末日的时刻。\n佛巴林卡塔尔等海", + "block_bbox": [ + 15, + 1, + 1027, + 289 + ], + "block_id": 0, + "block_order": 1, + "group_id": 0, + "block_polygon_points": [ + [ + 15.0, + 1.0 + ], + [ + 1027.0, + 1.0 + ], + [ + 1027.0, + 289.0 + ], + [ + 15.0, + 289.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "", + "block_bbox": [ + 1113, + 0, + 1697, + 254 + ], + "block_id": 1, + "block_order": 2, + "group_id": 0, + "block_polygon_points": [ + [ + 1113.0, + -3.0 + ], + [ + 1697.0, + -3.0 + ], + [ + 1697.0, + 254.0 + ], + [ + 1113.0, + 254.0 + ] + ] + }, + { + "block_label": "text", + "block_content": "很多消费者没有认识到医学验光的重要性,导致诸多后果。\n特许商品的销售便逐渐升温。文化软实力作出重要贡献。", + "block_bbox": [ + 18, + 327, + 1758, + 640 + ], + "block_id": 2, + "block_order": 3, + "group_id": 2, + "block_polygon_points": [ + [ + 18.0, + 327.0 + ], + [ + 1758.0, + 327.0 + ], + [ + 1758.0, + 640.0 + ], + [ + 18.0, + 640.0 + ] + ] + } + ], + "layout_det_res": { + "input_path": null, + "page_index": null, + "boxes": [ + { + "cls_id": 22, + "label": "text", + "score": 0.6567577123641968, + "coordinate": [ + 15, + 1, + 1027, + 289 + ], + "order": 1, + "polygon_points": [ + [ + 15.0, + 1.0 + ], + [ + 1027.0, + 1.0 + ], + [ + 1027.0, + 289.0 + ], + [ + 15.0, + 289.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.3265937566757202, + "coordinate": [ + 1122, + 0, + 1698, + 125 + ], + "order": 2, + "polygon_points": [ + [ + 1122.0, + -1.0 + ], + [ + 1698.0, + -1.0 + ], + [ + 1698.0, + 125.0 + ], + [ + 1122.0, + 125.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.39340317249298096, + "coordinate": [ + 1113, + 0, + 1697, + 254 + ], + "order": 3, + "polygon_points": [ + [ + 1113.0, + -3.0 + ], + [ + 1697.0, + -3.0 + ], + [ + 1697.0, + 254.0 + ], + [ + 1113.0, + 254.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.3441658616065979, + "coordinate": [ + 27, + 331, + 1372, + 460 + ], + "order": 4, + "polygon_points": [ + [ + 26.872575759887695, + 339.82818603515625 + ], + [ + 1370.701171875, + 327.748779296875 + ], + [ + 1371.77294921875, + 446.9930419921875 + ], + [ + 27.9443359375, + 459.07244873046875 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.411662220954895, + "coordinate": [ + 18, + 327, + 1758, + 640 + ], + "order": 5, + "polygon_points": [ + [ + 18.0, + 327.0 + ], + [ + 1758.0, + 327.0 + ], + [ + 1758.0, + 640.0 + ], + [ + 18.0, + 640.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.42693009972572327, + "coordinate": [ + 27, + 492, + 842, + 638 + ], + "order": 6, + "polygon_points": [ + [ + 27.0, + 502.0 + ], + [ + 27.0, + 580.0 + ], + [ + 45.0, + 590.0 + ], + [ + 281.0, + 593.0 + ], + [ + 650.0, + 631.0 + ], + [ + 841.0, + 631.0 + ], + [ + 833.0, + 569.0 + ], + [ + 798.0, + 546.0 + ], + [ + 430.0, + 508.0 + ], + [ + 36.0, + 492.0 + ] + ] + }, + { + "cls_id": 22, + "label": "text", + "score": 0.3693902790546417, + "coordinate": [ + 1037, + 491, + 1758, + 634 + ], + "order": 7, + "polygon_points": [ + [ + 1037.260009765625, + 487.0445556640625 + ], + [ + 1763.053955078125, + 504.2623291015625 + ], + [ + 1760.0, + 633.0001220703125 + ], + [ + 1034.2060546875, + 615.7823486328125 + ] + ] + } + ] + }, + "source_type": "image_ocr" + } +} \ No newline at end of file diff --git a/outputs/images/手写01_png/result.md b/outputs/images/手写01_png/result.md new file mode 100644 index 0000000..d4fa45e --- /dev/null +++ b/outputs/images/手写01_png/result.md @@ -0,0 +1,13 @@ +最优质的草场。但是这两年由于旱獭和草原黄鼠的逐年 + +保护,人们的行为需要矫正。 + +部分。末日的时刻。 + +佛巴林卡塔尔等海 + + + +很多消费者没有认识到医学验光的重要性,导致诸多后果。 + +特许商品的销售便逐渐升温。文化软实力作出重要贡献。 diff --git a/outputs/images/手写01_png/result.txt b/outputs/images/手写01_png/result.txt new file mode 100644 index 0000000..1dfce58 --- /dev/null +++ b/outputs/images/手写01_png/result.txt @@ -0,0 +1,7 @@ +最优质的草场。但是这两年由于旱獭和草原黄鼠的逐年 +保护,人们的行为需要矫正。 +部分。末日的时刻。 +佛巴林卡塔尔等海 + +很多消费者没有认识到医学验光的重要性,导致诸多后果。 +特许商品的销售便逐渐升温。文化软实力作出重要贡献。 diff --git a/outputs/pdfs/化肥买卖合同_GF_2000_0102/document.json b/outputs/pdfs/化肥买卖合同_GF_2000_0102/document.json new file mode 100644 index 0000000..2620812 --- /dev/null +++ b/outputs/pdfs/化肥买卖合同_GF_2000_0102/document.json @@ -0,0 +1,223 @@ +{ + "manifest": { + "manifest_version": 2, + "document_name": "化肥买卖合同　GF—2000—0102", + "input": { + "path": "D:\\Dev\\ocr-VL1.6\\data\\documents\\化肥买卖合同　GF—2000—0102.pdf", + "sha256": "a317a173b477162ad75560335d93939e7509ead4b43db888e16ea6b40d922549", + "size_bytes": 652474 + }, + "page_count": 2, + "selected_pages": [ + 1, + 2 + ], + "mode": "hybrid", + "text_layer_policy": { + "min_chars": 50, + "min_printable_ratio": 0.85, + "min_content_ratio": 0.6, + "max_replacement_ratio": 0.02, + "min_chars_per_megapixel": 25.0 + }, + "render": { + "dpi": 144, + "format": "png" + }, + "run_metadata": { + "device": "cpu", + "device_name": null, + "cpu_threads": null, + "python_version": "3.13.13", + "platform": "Windows-11-10.0.26200-SP0", + "paddle_version": null, + "pipeline_version": "v1.6", + "runtime_import_seconds": 0.0, + "runtime_setup_seconds": 0.0, + "model_init_seconds": 0.0 + }, + "status": "completed", + "created_at": "2026-07-16T16:20:10.471601+08:00", + "updated_at": "2026-07-16T16:20:10.522497+08:00", + "pages": { + "1": { + "status": "completed", + "page_number": 1, + "source_type": "text", + "routing_reason": "usable_text_layer", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 309, + "non_whitespace_chars": 251, + "printable_ratio": 1.0, + "content_ratio": 0.8566, + "replacement_ratio": 0.0, + "chars_per_megapixel": 500.841 + }, + "text_extract_seconds": 0.008, + "render_seconds": 0.0, + "ocr_seconds": 0.0, + "export_seconds": 0.003, + "total_seconds": 0.012, + "layout_boxes": 0, + "parsed_blocks": 1, + "completed_at": "2026-07-16T16:20:10.484568+08:00", + "state_save_seconds": 0.028 + }, + "2": { + "status": "completed", + "page_number": 2, + "source_type": "text", + "routing_reason": "usable_text_layer", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 462, + "non_whitespace_chars": 371, + "printable_ratio": 1.0, + "content_ratio": 0.8194, + "replacement_ratio": 0.0, + "chars_per_megapixel": 740.287 + }, + "text_extract_seconds": 0.002, + "render_seconds": 0.0, + "ocr_seconds": 0.0, + "export_seconds": 0.002, + "total_seconds": 0.004, + "layout_boxes": 0, + "parsed_blocks": 1, + "completed_at": "2026-07-16T16:20:10.518405+08:00", + "state_save_seconds": 0.003 + } + }, + "summary": { + "selected_pages": 2, + "completed_pages": 2, + "completed_before_resume": 0, + "text_pages": 2, + "ocr_pages": 0, + "failed_pages": [], + "model_used": false, + "model_initialized_during_task": false, + "model_available": false, + "timing": { + "pdf_open_seconds": 0.001, + "manifest_prepare_seconds": 0.003, + "text_extract_total_seconds": 0.01, + "render_total_seconds": 0.0, + "ocr_total_seconds": 0.0, + "export_total_seconds": 0.005, + "state_save_total_seconds": 0.031, + "page_total_seconds": 0.016, + "model_init_seconds": 0.0, + "finalize_seconds": 0.003, + "task_total_seconds": 0.056 + } + } + }, + "page_results": [ + { + "page_number": 1, + "source_type": "text", + "metrics": { + "status": "completed", + "page_number": 1, + "source_type": "text", + "routing_reason": "usable_text_layer", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 309, + "non_whitespace_chars": 251, + "printable_ratio": 1.0, + "content_ratio": 0.8566, + "replacement_ratio": 0.0, + "chars_per_megapixel": 500.841 + }, + "text_extract_seconds": 0.008, + "render_seconds": 0.0, + "ocr_seconds": 0.0, + "export_seconds": 0.003, + "total_seconds": 0.012, + "layout_boxes": 0, + "parsed_blocks": 1, + "completed_at": "2026-07-16T16:20:10.484568+08:00", + "state_save_seconds": 0.028 + }, + "result": { + "res": { + "input_path": "D:\\Dev\\ocr-VL1.6\\data\\documents\\化肥买卖合同　GF—2000—0102.pdf", + "page_index": 0, + "page_number": 1, + "page_count": 2, + "source_type": "text", + "text": "1\nGF—2000—0102\n化肥买卖合同\n（示范文本）\n合同编号：\n出卖人：　　　　　 签订地点：\n买受人：　　　　　 签订时间： 年 月 日\n第一条　标的、数量、价款及交（提）货时间\n化肥\n名称\n商标或\n品牌 规格 生产厂家\n计量\n单位 数量 单价 金额\n交（提）货时间及数量\n合计\n合计人民币金额（大写）：\n（注：空格如不够用，可以另接）\n第二条 　质量标准：\n第三条 　出卖人对质量负责的期限：\n第四条　包装标准：\n第五条　合理损耗标准及计算方法：\n第六条　化肥的所有权自 　　时起转移，但买受人未履行支付价款义务的，化肥属于\n所有。\n第七条　交（提）货方式、地点：\n第八条　运输方式和到达站（港）及费用负担：", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 309, + "non_whitespace_chars": 251, + "printable_ratio": 1.0, + "content_ratio": 0.8566, + "replacement_ratio": 0.0, + "chars_per_megapixel": 500.841 + }, + "width_points": 595.2760009765625, + "height_points": 841.8900146484375 + } + } + }, + { + "page_number": 2, + "source_type": "text", + "metrics": { + "status": "completed", + "page_number": 2, + "source_type": "text", + "routing_reason": "usable_text_layer", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 462, + "non_whitespace_chars": 371, + "printable_ratio": 1.0, + "content_ratio": 0.8194, + "replacement_ratio": 0.0, + "chars_per_megapixel": 740.287 + }, + "text_extract_seconds": 0.002, + "render_seconds": 0.0, + "ocr_seconds": 0.0, + "export_seconds": 0.002, + "total_seconds": 0.004, + "layout_boxes": 0, + "parsed_blocks": 1, + "completed_at": "2026-07-16T16:20:10.518405+08:00", + "state_save_seconds": 0.003 + }, + "result": { + "res": { + "input_path": "D:\\Dev\\ocr-VL1.6\\data\\documents\\化肥买卖合同　GF—2000—0102.pdf", + "page_index": 1, + "page_number": 2, + "page_count": 2, + "source_type": "text", + "text": "2\n第九条　检验标准、方法、地点及期限：\n第十条　结算方式、时间及地点：\n第十一条　本合同解除的条件：\n第十二条　违约责任：\n第十三条　担保方式（也可另立担保合同）：\n第十四条　合同争议的解决方式：本合同在履行过程中发生的争议，由双方当事人协商解\n决；也可由当地工商行政管理部门调解；协商或调解不成的，按下列第　　　种方式解决：\n（一）提交　　　　　　仲裁委员会仲裁；\n（二）依法向人民法院起诉。\n第十五条　本合同自　　　　　　起生效。\n第十六条　其他约定事项：\n出卖人\n出卖人（章）：\n住所：\n法定代表人：\n( 章或签字 )：\n居民身份证号码：\n委托代理人：\n电话：\n传真：\n开户银行：\n账号：\n邮政编码：\n买受人\n买受人（章）：\n住所：\n法定代表人：\n( 章或签字 )：\n居民身份证号码：\n委托代理人：\n电话：\n传真：\n开户银行：\n账号：\n邮政编码：\n鉴（公）证意见：\n鉴（公）证机关（章）\n经办人：\n年　月　日\n（提示：化肥经销企业应具有相应的主体资格）\n监制部门：　　　　　　　　　　　　　　　　　　　　 印制单位：", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 462, + "non_whitespace_chars": 371, + "printable_ratio": 1.0, + "content_ratio": 0.8194, + "replacement_ratio": 0.0, + "chars_per_megapixel": 740.287 + }, + "width_points": 595.2760009765625, + "height_points": 841.8900146484375 + } + } + } + ] +} \ No newline at end of file diff --git a/outputs/pdfs/化肥买卖合同_GF_2000_0102/document.md b/outputs/pdfs/化肥买卖合同_GF_2000_0102/document.md new file mode 100644 index 0000000..2da0442 --- /dev/null +++ b/outputs/pdfs/化肥买卖合同_GF_2000_0102/document.md @@ -0,0 +1,79 @@ +# 化肥买卖合同　GF—2000—0102 + +--- + +## Page 1 (text) + +1 +GF—2000—0102 +化肥买卖合同 +（示范文本） +合同编号： +出卖人：　　　　　 签订地点： +买受人：　　　　　 签订时间： 年 月 日 +第一条　标的、数量、价款及交（提）货时间 +化肥 +名称 +商标或 +品牌 规格 生产厂家 +计量 +单位 数量 单价 金额 +交（提）货时间及数量 +合计 +合计人民币金额（大写）： +（注：空格如不够用，可以另接） +第二条 　质量标准： +第三条 　出卖人对质量负责的期限： +第四条　包装标准： +第五条　合理损耗标准及计算方法： +第六条　化肥的所有权自 　　时起转移，但买受人未履行支付价款义务的，化肥属于 +所有。 +第七条　交（提）货方式、地点： +第八条　运输方式和到达站（港）及费用负担： + +--- + +## Page 2 (text) + +2 +第九条　检验标准、方法、地点及期限： +第十条　结算方式、时间及地点： +第十一条　本合同解除的条件： +第十二条　违约责任： +第十三条　担保方式（也可另立担保合同）： +第十四条　合同争议的解决方式：本合同在履行过程中发生的争议，由双方当事人协商解 +决；也可由当地工商行政管理部门调解；协商或调解不成的，按下列第　　　种方式解决： +（一）提交　　　　　　仲裁委员会仲裁； +（二）依法向人民法院起诉。 +第十五条　本合同自　　　　　　起生效。 +第十六条　其他约定事项： +出卖人 +出卖人（章）： +住所： +法定代表人： +( 章或签字 )： +居民身份证号码： +委托代理人： +电话： +传真： +开户银行： +账号： +邮政编码： +买受人 +买受人（章）： +住所： +法定代表人： +( 章或签字 )： +居民身份证号码： +委托代理人： +电话： +传真： +开户银行： +账号： +邮政编码： +鉴（公）证意见： +鉴（公）证机关（章） +经办人： +年　月　日 +（提示：化肥经销企业应具有相应的主体资格） +监制部门：　　　　　　　　　　　　　　　　　　　　 印制单位： diff --git a/outputs/pdfs/化肥买卖合同_GF_2000_0102/manifest.json b/outputs/pdfs/化肥买卖合同_GF_2000_0102/manifest.json new file mode 100644 index 0000000..2338e01 --- /dev/null +++ b/outputs/pdfs/化肥买卖合同_GF_2000_0102/manifest.json @@ -0,0 +1,117 @@ +{ + "manifest_version": 2, + "document_name": "化肥买卖合同　GF—2000—0102", + "input": { + "path": "D:\\Dev\\ocr-VL1.6\\data\\documents\\化肥买卖合同　GF—2000—0102.pdf", + "sha256": "a317a173b477162ad75560335d93939e7509ead4b43db888e16ea6b40d922549", + "size_bytes": 652474 + }, + "page_count": 2, + "selected_pages": [ + 1, + 2 + ], + "mode": "hybrid", + "text_layer_policy": { + "min_chars": 50, + "min_printable_ratio": 0.85, + "min_content_ratio": 0.6, + "max_replacement_ratio": 0.02, + "min_chars_per_megapixel": 25.0 + }, + "render": { + "dpi": 144, + "format": "png" + }, + "run_metadata": { + "device": "cpu", + "device_name": null, + "cpu_threads": null, + "python_version": "3.13.13", + "platform": "Windows-11-10.0.26200-SP0", + "paddle_version": null, + "pipeline_version": "v1.6", + "runtime_import_seconds": 0.0, + "runtime_setup_seconds": 0.0, + "model_init_seconds": 0.0 + }, + "status": "completed", + "created_at": "2026-07-16T16:20:10.471601+08:00", + "updated_at": "2026-07-16T16:20:10.522497+08:00", + "pages": { + "1": { + "status": "completed", + "page_number": 1, + "source_type": "text", + "routing_reason": "usable_text_layer", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 309, + "non_whitespace_chars": 251, + "printable_ratio": 1.0, + "content_ratio": 0.8566, + "replacement_ratio": 0.0, + "chars_per_megapixel": 500.841 + }, + "text_extract_seconds": 0.008, + "render_seconds": 0.0, + "ocr_seconds": 0.0, + "export_seconds": 0.003, + "total_seconds": 0.012, + "layout_boxes": 0, + "parsed_blocks": 1, + "completed_at": "2026-07-16T16:20:10.484568+08:00", + "state_save_seconds": 0.028 + }, + "2": { + "status": "completed", + "page_number": 2, + "source_type": "text", + "routing_reason": "usable_text_layer", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 462, + "non_whitespace_chars": 371, + "printable_ratio": 1.0, + "content_ratio": 0.8194, + "replacement_ratio": 0.0, + "chars_per_megapixel": 740.287 + }, + "text_extract_seconds": 0.002, + "render_seconds": 0.0, + "ocr_seconds": 0.0, + "export_seconds": 0.002, + "total_seconds": 0.004, + "layout_boxes": 0, + "parsed_blocks": 1, + "completed_at": "2026-07-16T16:20:10.518405+08:00", + "state_save_seconds": 0.003 + } + }, + "summary": { + "selected_pages": 2, + "completed_pages": 2, + "completed_before_resume": 0, + "text_pages": 2, + "ocr_pages": 0, + "failed_pages": [], + "model_used": false, + "model_initialized_during_task": false, + "model_available": false, + "timing": { + "pdf_open_seconds": 0.001, + "manifest_prepare_seconds": 0.003, + "text_extract_total_seconds": 0.01, + "render_total_seconds": 0.0, + "ocr_total_seconds": 0.0, + "export_total_seconds": 0.005, + "state_save_total_seconds": 0.031, + "page_total_seconds": 0.016, + "model_init_seconds": 0.0, + "finalize_seconds": 0.003, + "task_total_seconds": 0.056 + } + } +} \ No newline at end of file diff --git a/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0001.json b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0001.json new file mode 100644 index 0000000..0f7b95d --- /dev/null +++ b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0001.json @@ -0,0 +1,22 @@ +{ + "res": { + "input_path": "D:\\Dev\\ocr-VL1.6\\data\\documents\\化肥买卖合同　GF—2000—0102.pdf", + "page_index": 0, + "page_number": 1, + "page_count": 2, + "source_type": "text", + "text": "1\nGF—2000—0102\n化肥买卖合同\n（示范文本）\n合同编号：\n出卖人：　　　　　 签订地点：\n买受人：　　　　　 签订时间： 年 月 日\n第一条　标的、数量、价款及交（提）货时间\n化肥\n名称\n商标或\n品牌 规格 生产厂家\n计量\n单位 数量 单价 金额\n交（提）货时间及数量\n合计\n合计人民币金额（大写）：\n（注：空格如不够用，可以另接）\n第二条 　质量标准：\n第三条 　出卖人对质量负责的期限：\n第四条　包装标准：\n第五条　合理损耗标准及计算方法：\n第六条　化肥的所有权自 　　时起转移，但买受人未履行支付价款义务的，化肥属于\n所有。\n第七条　交（提）货方式、地点：\n第八条　运输方式和到达站（港）及费用负担：", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 309, + "non_whitespace_chars": 251, + "printable_ratio": 1.0, + "content_ratio": 0.8566, + "replacement_ratio": 0.0, + "chars_per_megapixel": 500.841 + }, + "width_points": 595.2760009765625, + "height_points": 841.8900146484375 + } +} \ No newline at end of file diff --git a/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0001.md b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0001.md new file mode 100644 index 0000000..48a50cb --- /dev/null +++ b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0001.md @@ -0,0 +1,26 @@ +1 +GF—2000—0102 +化肥买卖合同 +（示范文本） +合同编号： +出卖人：　　　　　 签订地点： +买受人：　　　　　 签订时间： 年 月 日 +第一条　标的、数量、价款及交（提）货时间 +化肥 +名称 +商标或 +品牌 规格 生产厂家 +计量 +单位 数量 单价 金额 +交（提）货时间及数量 +合计 +合计人民币金额（大写）： +（注：空格如不够用，可以另接） +第二条 　质量标准： +第三条 　出卖人对质量负责的期限： +第四条　包装标准： +第五条　合理损耗标准及计算方法： +第六条　化肥的所有权自 　　时起转移，但买受人未履行支付价款义务的，化肥属于 +所有。 +第七条　交（提）货方式、地点： +第八条　运输方式和到达站（港）及费用负担： diff --git a/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0002.json b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0002.json new file mode 100644 index 0000000..a052d98 --- /dev/null +++ b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0002.json @@ -0,0 +1,22 @@ +{ + "res": { + "input_path": "D:\\Dev\\ocr-VL1.6\\data\\documents\\化肥买卖合同　GF—2000—0102.pdf", + "page_index": 1, + "page_number": 2, + "page_count": 2, + "source_type": "text", + "text": "2\n第九条　检验标准、方法、地点及期限：\n第十条　结算方式、时间及地点：\n第十一条　本合同解除的条件：\n第十二条　违约责任：\n第十三条　担保方式（也可另立担保合同）：\n第十四条　合同争议的解决方式：本合同在履行过程中发生的争议，由双方当事人协商解\n决；也可由当地工商行政管理部门调解；协商或调解不成的，按下列第　　　种方式解决：\n（一）提交　　　　　　仲裁委员会仲裁；\n（二）依法向人民法院起诉。\n第十五条　本合同自　　　　　　起生效。\n第十六条　其他约定事项：\n出卖人\n出卖人（章）：\n住所：\n法定代表人：\n( 章或签字 )：\n居民身份证号码：\n委托代理人：\n电话：\n传真：\n开户银行：\n账号：\n邮政编码：\n买受人\n买受人（章）：\n住所：\n法定代表人：\n( 章或签字 )：\n居民身份证号码：\n委托代理人：\n电话：\n传真：\n开户银行：\n账号：\n邮政编码：\n鉴（公）证意见：\n鉴（公）证机关（章）\n经办人：\n年　月　日\n（提示：化肥经销企业应具有相应的主体资格）\n监制部门：　　　　　　　　　　　　　　　　　　　　 印制单位：", + "text_layer": { + "usable": true, + "reason": "usable_text_layer", + "raw_chars": 462, + "non_whitespace_chars": 371, + "printable_ratio": 1.0, + "content_ratio": 0.8194, + "replacement_ratio": 0.0, + "chars_per_megapixel": 740.287 + }, + "width_points": 595.2760009765625, + "height_points": 841.8900146484375 + } +} \ No newline at end of file diff --git a/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0002.md b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0002.md new file mode 100644 index 0000000..33ac1ef --- /dev/null +++ b/outputs/pdfs/化肥买卖合同_GF_2000_0102/pages/page-0002.md @@ -0,0 +1,42 @@ +2 +第九条　检验标准、方法、地点及期限： +第十条　结算方式、时间及地点： +第十一条　本合同解除的条件： +第十二条　违约责任： +第十三条　担保方式（也可另立担保合同）： +第十四条　合同争议的解决方式：本合同在履行过程中发生的争议，由双方当事人协商解 +决；也可由当地工商行政管理部门调解；协商或调解不成的，按下列第　　　种方式解决： +（一）提交　　　　　　仲裁委员会仲裁； +（二）依法向人民法院起诉。 +第十五条　本合同自　　　　　　起生效。 +第十六条　其他约定事项： +出卖人 +出卖人（章）： +住所： +法定代表人： +( 章或签字 )： +居民身份证号码： +委托代理人： +电话： +传真： +开户银行： +账号： +邮政编码： +买受人 +买受人（章）： +住所： +法定代表人： +( 章或签字 )： +居民身份证号码： +委托代理人： +电话： +传真： +开户银行： +账号： +邮政编码： +鉴（公）证意见： +鉴（公）证机关（章） +经办人： +年　月　日 +（提示：化肥经销企业应具有相应的主体资格） +监制部门：　　　　　　　　　　　　　　　　　　　　 印制单位：