3 réponses
- Le plus récent
- Le plus de votes
- La plupart des commentaires
0
Hi Jacek
May you please share the contents of the "annotation-ref" json from the sample line you have shared above. It is located at: "s3://comprehend-semi-structured-docs-us-east-1-11111111111/output/first-job-for-Jacek-and-Matt-labeling-job-20230517T115059/annotations/consolidated-annotation/consolidation-response/iteration-1/annotations/I9-001f-1-7a2216d3-ann.json"
0
In meantime I removed previous files but I am sharing new files even with less data but I still get the same error for these files when I use them to train a new model.
output.manifest
{"source-ref":"s3://comprehend-semi-structured-docs-us-east-1-111111111111/src_02/I-9_003.pdf","page":"1","metadata":{"pages":"1","use-textract-only":false,"labels":["LastName","FirstName"]},"annotator-metadata":{"info":"I hope it will work","Priority":"It has medium priority"},"job-for-labeling-02-labeling-job-20230518T063720":{"annotation-ref":"s3://comprehend-semi-structured-docs-us-east-1-111111111111/output/job-for-labeling-02-labeling-job-20230518T063720/annotations/consolidated-annotation/consolidation-response/iteration-1/annotations/I-9_003-1-1419c853-ann.json"},"job-for-labeling-02-labeling-job-20230518T063720-metadata":{"type":"groundtruth/custom","job-name":"job-for-labeling-02-labeling-job-20230518t063720","human-annotated":"yes","creation-date":"2023-05-18T06:41:59.467000"}} {"source-ref":"s3://comprehend-semi-structured-docs-us-east-1-111111111111/src_02/I-9_002.pdf","page":"1","metadata":{"pages":"1","use-textract-only":false,"labels":["LastName","FirstName"]},"annotator-metadata":{"info":"I hope it will work","Priority":"It has medium priority"},"job-for-labeling-02-labeling-job-20230518T063720":{"annotation-ref":"s3://comprehend-semi-structured-docs-us-east-1-111111111111/output/job-for-labeling-02-labeling-job-20230518T063720/annotations/consolidated-annotation/consolidation-response/iteration-1/annotations/I-9_002-1-5dc996bf-ann.json"},"job-for-labeling-02-labeling-job-20230518T063720-metadata":{"type":"groundtruth/custom","job-name":"job-for-labeling-02-labeling-job-20230518t063720","human-annotated":"yes","creation-date":"2023-05-18T06:41:59.504000"}} {"source-ref":"s3://comprehend-semi-structured-docs-us-east-1-111111111111/src_02/I-9_001.pdf","page":"1","metadata":{"pages":"1","use-textract-only":false,"labels":["LastName","FirstName"]},"annotator-metadata":{"info":"I hope it will work","Priority":"It has medium priority"},"job-for-labeling-02-labeling-job-20230518T063720":{"annotation-ref":"s3://comprehend-semi-structured-docs-us-east-1-111111111111/output/job-for-labeling-02-labeling-job-20230518T063720/annotations/consolidated-annotation/consolidation-response/iteration-1/annotations/I-9_001-1-5241949c-ann.json"},"job-for-labeling-02-labeling-job-20230518T063720-metadata":{"type":"groundtruth/custom","job-name":"job-for-labeling-02-labeling-job-20230518t063720","human-annotated":"yes","creation-date":"2023-05-18T06:43:05.079000"}}
I-9_003-1-1419c853-ann.json
{ "Blocks": [ { "BlockType": "LINE", "Id": "6f1f5d4b-c5bd-4474-9bfd-1a4aab73dead", "Text": "Employment Eligibility Verification USCIS", "Geometry": { "BoundingBox": { "Width": 0.578890522875817, "Top": 0.03134469696969697, "Left": 0.32302287581699348, "Height": 0.016321969696969697 }, "Polygon": [ { "X": 0.32302287581699348, "Y": 0.03134469696969697 }, { "X": 0.9019133986928105, "Y": 0.03134469696969697 }, { "X": 0.9019133986928105, "Y": 0.04766666666666666 }, { "X": 0.32302287581699348, "Y": 0.04766666666666666 } ] }, "Relationships": [ { "Ids": [ "40893cf7-2e45-4e10-802a-c7c8b96dbe6b", "1516182f-5b28-4dc3-904e-8411f42be966", "96fca50a-f19f-40f0-8124-fcfacb999594", "2fb46811-30e5-4b48-9e69-e75946dacb2a" ], "Type": "CHILD" } ], "Page": 1 }, { "BlockType": "WORD", "Id": "40893cf7-2e45-4e10-802a-c7c8b96dbe6b", "Text": "Employment", "Geometry": { "BoundingBox": { "Width": 0.10801960784313726, "Top": 0.03251515151515151, "Left": 0.32302287581699348, "Height": 0.015151515151515152 }, "Polygon": [ { "X": 0.32302287581699348, "Y": 0.03251515151515151 }, { "X": 0.4310424836601307, "Y": 0.03251515151515151 }, { "X": 0.4310424836601307, "Y": 0.04766666666666666 }, { "X": 0.32302287581699348, "Y": 0.04766666666666666 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "1516182f-5b28-4dc3-904e-8411f42be966", "Text": "Eligibility", "Geometry": { "BoundingBox": { "Width": 0.08268627450980393, "Top": 0.03251515151515151, "Left": 0.43594444444444449, "Height": 0.015151515151515152 }, "Polygon": [ { "X": 0.43594444444444449, "Y": 0.03251515151515151 }, { "X": 0.5186307189542484, "Y": 0.03251515151515151 }, { "X": 0.5186307189542484, "Y": 0.04766666666666666 }, { "X": 0.43594444444444449, "Y": 0.04766666666666666 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "96fca50a-f19f-40f0-8124-fcfacb999594", "Text": "Verification", "Geometry": { "BoundingBox": { "Width": 0.10011764705882354, "Top": 0.03251515151515151, "Left": 0.5232777777777777, "Height": 0.015151515151515152 }, "Polygon": [ { "X": 0.5232777777777777, "Y": 0.03251515151515151 }, { "X": 0.6233954248366013, "Y": 0.03251515151515151 }, { "X": 0.6233954248366013, "Y": 0.04766666666666666 }, { "X": 0.5232777777777777, "Y": 0.04766666666666666 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "2fb46811-30e5-4b48-9e69-e75946dacb2a", "Text": "USCIS", "Geometry": { "BoundingBox": { "Width": 0.05292647058823529, "Top": 0.03134469696969697, "Left": 0.8489869281045752, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.8489869281045752, "Y": 0.03134469696969697 }, { "X": 0.9019133986928105, "Y": 0.03134469696969697 }, { "X": 0.9019133986928105, "Y": 0.045284090909090909 }, { "X": 0.8489869281045752, "Y": 0.045284090909090909 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "LINE", "Id": "89f02916-fe15-4221-b583-308e502dd7ed", "Text": "Form I-9", "Geometry": { "BoundingBox": { "Width": 0.0694117647058825, "Top": 0.04801136363636364, "Left": 0.8409477124183006, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.8409477124183006, "Y": 0.04801136363636364 }, { "X": 0.9103594771241831, "Y": 0.04801136363636364 }, { "X": 0.9103594771241831, "Y": 0.061950757575757579 }, { "X": 0.8409477124183006, "Y": 0.061950757575757579 } ] }, "Relationships": [ { "Ids": [ "8c93cfde-2682-4a58-a72a-2956699f5f35", "0aa40458-88cf-4244-944f-c2edf2bd12af" ], "Type": "CHILD" } ], "Page": 1 }, { "BlockType": "WORD", "Id": "8c93cfde-2682-4a58-a72a-2956699f5f35", "Text": "Form", "Geometry": { "BoundingBox": { "Width": 0.04307843137254902, "Top": 0.04801136363636364, "Left": 0.8409477124183006, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.8409477124183006, "Y": 0.04801136363636364 }, { "X": 0.8840261437908497, "Y": 0.04801136363636364 }, { "X": 0.8840261437908497, "Y": 0.061950757575757579 }, { "X": 0.8409477124183006, "Y": 0.061950757575757579 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "0aa40458-88cf-4244-944f-c2edf2bd12af", "Text": "I-9", "Geometry": { "BoundingBox": { "Width": 0.02215686274509804, "Top": 0.04801136363636364, "Left": 0.888202614379085, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.888202614379085, "Y": 0.04801136363636364 }, { "X": 0.9103594771241831, "Y": 0.04801136363636364 }, { "X": 0.9103594771241831, "Y": 0.061950757575757579 }, { "X": 0.888202614379085, "Y": 0.061950757575757579 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "LINE", "Id": "a676e7a0-71e5-4b6c-9ecb-30f0ac39a4aa", "Text": "Department of Homeland Security", "Geometry": { "BoundingBox": { "Width": 0.2651764705882353, "Top": 0.05422348484848485, "Left": 0.3379248366013072, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.3379248366013072, "Y": 0.05422348484848485 }, { "X": 0.6031013071895425, "Y": 0.05422348484848485 }, { "X": 0.6031013071895425, "Y": 0.06816287878787879 }, { "X": 0.3379248366013072, "Y": 0.06816287878787879 } ] }, "Relationships": [ { "Ids": [ "34c1d0c0-b7b2-4b84-a6da-a0306eb18d54", "adecd3fc-d54e-423d-80f4-5115fd76801f", "c7135e9e-d61a-49ee-809a-5e167005a3fc", "7658976a-32a0-4674-b257-97a6d83b2a8d" ], "Type": "CHILD" } ], "Page": 1 }, { "BlockType": "WORD", "Id": "34c1d0c0-b7b2-4b84-a6da-a0306eb18d54", "Text": "Department", "Geometry": { "BoundingBox": { "Width": 0.09284803921568628, "Top": 0.05422348484848485, "Left": 0.3379248366013072, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.3379248366013072, "Y": 0.05422348484848485 }, { "X": 0.4307728758169935, "Y": 0.05422348484848485 }, { "X": 0.4307728758169935, "Y": 0.06816287878787879 }, { "X": 0.3379248366013072, "Y": 0.06816287878787879 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "adecd3fc-d54e-423d-80f4-5115fd76801f", "Text": "of", "Geometry": { "BoundingBox": { "Width": 0.015026143790849673, "Top": 0.05422348484848485, "Left": 0.43533660130718956, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.43533660130718956, "Y": 0.05422348484848485 }, { "X": 0.4503627450980392, "Y": 0.05422348484848485 }, { "X": 0.4503627450980392, "Y": 0.06816287878787879 }, { "X": 0.43533660130718956, "Y": 0.06816287878787879 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "c7135e9e-d61a-49ee-809a-5e167005a3fc", "Text": "Homeland", "Geometry": { "BoundingBox": { "Width": 0.08002124183006536, "Top": 0.05422348484848485, "Left": 0.45472875816993466, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.45472875816993466, "Y": 0.05422348484848485 }, { "X": 0.53475, "Y": 0.05422348484848485 }, { "X": 0.53475, "Y": 0.06816287878787879 }, { "X": 0.45472875816993466, "Y": 0.06816287878787879 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "7658976a-32a0-4674-b257-97a6d83b2a8d", "Text": "Security", "Geometry": { "BoundingBox": { "Width": 0.06409313725490197, "Top": 0.05422348484848485, "Left": 0.5390081699346405, "Height": 0.013939393939393939 }, "Polygon": [ { "X": 0.5390081699346405, "Y": 0.05422348484848485 }, { "X": 0.6031013071895425, "Y": 0.05422348484848485 }, { "X": 0.6031013071895425, "Y": 0.06816287878787879 }, { "X": 0.5390081699346405, "Y": 0.06816287878787879 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "LINE", "Id": "932b6392-79b7-4ebc-8c2c-308c27776c3a", "Text": "OMB No. 1615-0047", "Geometry": { "BoundingBox": { "Width": 0.11224836601307187, "Top": 0.06476893939393939, "Left": 0.8193790849673203, "Height": 0.010151515151515148 }, "Polygon": [ { "X": 0.8193790849673203, "Y": 0.06476893939393939 }, { "X": 0.9316274509803921, "Y": 0.06476893939393939 }, { "X": 0.9316274509803921, "Y": 0.07492045454545454 }, { "X": 0.8193790849673203, "Y": 0.07492045454545454 } ] }, "Relationships": [ { "Ids": [ "2ae600f4-2715-4c8f-af20-915ef9fcf1a8", "a9f4d9a4-6ffe-4f8e-b2ab-6459350f7ce1", "73f669bf-ecc4-4b75-9e7f-6fcf8fa030d8" ], "Type": "CHILD" } ], "Page": 1 }, { "BlockType": "WORD", "Id": "2ae600f4-2715-4c8f-af20-915ef9fcf1a8", "Text": "OMB", "Geometry": { "BoundingBox": { "Width": 0.029926470588235299, "Top": 0.06476893939393939, "Left": 0.8193790849673203, "Height": 0.010151515151515151 }, "Polygon": [ { "X": 0.8193790849673203, "Y": 0.06476893939393939 }, { "X": 0.8493055555555555, "Y": 0.06476893939393939 }, { "X": 0.8493055555555555, "Y": 0.07492045454545454 }, { "X": 0.8193790849673203, "Y": 0.07492045454545454 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "a9f4d9a4-6ffe-4f8e-b2ab-6459350f7ce1", "Text": "No.", "Geometry": { "BoundingBox": { "Width": 0.019142156862745099, "Top": 0.06476893939393939, "Left": 0.8526813725490197, "Height": 0.010151515151515151 }, "Polygon": [ { "X": 0.8526813725490197, "Y": 0.06476893939393939 }, { "X": 0.8718235294117648, "Y": 0.06476893939393939 }, { "X": 0.8718235294117648, "Y": 0.07492045454545454 }, { "X": 0.8526813725490197, "Y": 0.07492045454545454 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "73f669bf-ecc4-4b75-9e7f-6fcf8fa030d8", "Text": "1615-0047", "Geometry": { "BoundingBox": { "Width": 0.056625816993464059, "Top": 0.06476893939393939, "Left": 0.8750016339869281, "Height": 0.010151515151515151 }, "Polygon": [ { "X": 0.8750016339869281, "Y": 0.06476893939393939 }, { "X": 0.9316274509803921, "Y": 0.06476893939393939 }, { "X": 0.9316274509803921, "Y": 0.07492045454545454 }, { "X": 0.8750016339869281, "Y": 0.07492045454545454 } ] }, "Relationships": [], "Page": 1 }, { "BlockType": "LINE", "Id": "399fbd18-1ee5-47bc-ae34-ca318957f363", "Text": "U.S. Citizenship and Immigration Services", "Geometry": { "BoundingBox": { "Width": 0.3084346405228758, "Top": 0.07104166666666667, "Le
répondu il y a un an
0
I see that the content of file I-9_003-1-1419c853-ann.json has been cropped so I am adding here some lines from the bottom of the file.
}, "Relationships": [], "Page": 1 }, { "BlockType": "WORD", "Id": "1a6b5a92-0ded-489c-a299-dd883b778179", "Text": "3", "Geometry": { "BoundingBox": { "Width": 0.007352941176470588, "Top": 0.9692727272727273, "Left": 0.9340653594771242, "Height": 0.011363636363636364 }, "Polygon": [ { "X": 0.9340653594771242, "Y": 0.9692727272727273 }, { "X": 0.9414183006535948, "Y": 0.9692727272727273 }, { "X": 0.9414183006535948, "Y": 0.9806363636363636 }, { "X": 0.9340653594771242, "Y": 0.9806363636363636 } ] }, "Relationships": [], "Page": 1 } ], "BlocksS3Ref": "s3://comprehend-semi-structured-docs-us-east-1-111111111111/comprehend-semi-structured-docs-intermediate-output/job-for-labeling-02-labeling-job-20230518t063720/I-9_003_1_blocks.json", "DocumentMetadata": { "Pages": "1", "PageNumber": "1" }, "Version": "2021-04-30", "DocumentType": "NativePDF", "Entities": [ { "BlockReferences": [ { "BlockId": "3e4881f0-fa14-4a72-b31f-b3323817a36f", "ChildBlocks": [ { "BeginOffset": 0, "EndOffset": 35, "ChildBlockId": "94572034-c5d3-4b33-beec-9485d5ddcbeb" } ], "BeginOffset": 0, "EndOffset": 35 } ], "Text": "Wolfeschlegelsteinhausenbergerdorff", "Type": "LastName", "Score": 1 }, { "BlockReferences": [ { "BlockId": "3e4881f0-fa14-4a72-b31f-b3323817a36f", "ChildBlocks": [ { "BeginOffset": 0, "EndOffset": 6, "ChildBlockId": "025da007-2c08-4cc7-9b47-ee08e99b9a52" } ], "BeginOffset": 36, "EndOffset": 42 } ], "Text": "Hubert", "Type": "FirstName", "Score": 1 } ], "File": "I-9_003-1-1419c853-ann.json" }
répondu il y a un an
Contenus pertinents
- demandé il y a 6 mois
- demandé il y a 2 mois
- demandé il y a un an
- AWS OFFICIELA mis à jour il y a 3 ans
I thought that maybe the attribute name should not contain suffix with date time but I watched this https://youtu.be/oDk5aOd400c?t=366 and they use the attribute as it is together with the date time suffix.