mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 13:18:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: restrict click version and update lock file (#1582)

Browse Source 
* fix click dependency and update lock file

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-05-13 10:40:08 +02:00
committed by GitHub
parent 0d0fa6cbe3
commit 8baa85a49d
18 changed files with 1322 additions and 515 deletions
Download Patch File Download Diff File Expand all files Collapse all files

115
tests/data/groundtruth/docling_v1/2206.01062.json
View File

@@ -430,6 +430,29 @@
"type": "figure",
"$ref": "#/figures/0"
},
{
"prov": [
{
"bbox": [
317.95499,
232.48476000000005,
559.80579,
251.91701
],
"page": 1,
"span": [
0,
84
],
"__ref_s3_data": null
}
],
"text": "Figure 1: Four examples of complex page layouts across different document categories",
"type": "caption",
"payload": null,
"name": "Caption",
"font": null
},
{
"prov": [
{
@@ -964,6 +987,29 @@
"type": "figure",
"$ref": "#/figures/1"
},
{
"prov": [
{
"bbox": [
53.79800000000001,
536.45276,
294.04373,
555.88501
],
"page": 3,
"span": [
0,
69
],
"__ref_s3_data": null
}
],
"text": "Figure 2: Distribution of DocLayNet pages across document categories.",
"type": "caption",
"payload": null,
"name": "Caption",
"font": null
},
{
"prov": [
{
@@ -1227,6 +1273,29 @@
"type": "figure",
"$ref": "#/figures/2"
},
{
"prov": [
{
"bbox": [
53.79800000000001,
185.68075999999996,
295.64874,
237.99000999999998
],
"page": 4,
"span": [
0,
281
],
"__ref_s3_data": null
}
],
"text": "Figure 3: Corpus Conversion Service annotation user interface. The PDF page is shown in the background, with overlaid text-cells (in darker shades). The annotation boxes can be drawn by dragging a rectangle over each segment with the respective label from the palette on the right.",
"type": "caption",
"payload": null,
"name": "Caption",
"font": null
},
{
"prov": [
{
@@ -1808,6 +1877,29 @@
"type": "figure",
"$ref": "#/figures/4"
},
{
"prov": [
{
"bbox": [
317.95499,
449.71581999999995,
559.80579,
512.98401
],
"page": 6,
"span": [
0,
329
],
"__ref_s3_data": null
}
],
"text": "Figure 5: Prediction performance (mAP@0.5-0.95) of a Mask R-CNN network with ResNet50 backbone trained on increasing fractions of the DocLayNet dataset. The learning curve flattens around the 80% mark, indicating that increasing the size of the DocLayNet dataset with similar data will not yield significantly better predictions.",
"type": "caption",
"payload": null,
"name": "Caption",
"font": null
},
{
"prov": [
{
@@ -2702,6 +2794,29 @@
"type": "figure",
"$ref": "#/figures/5"
},
{
"prov": [
{
"bbox": [
62.323874999999994,
343.73517,
318.50473,
349.71457
],
"page": 9,
"span": [
0,
89
],
"__ref_s3_data": null
}
],
"text": "Text Caption List-Item Formula Table Section-Header Picture Page-Header Page-Footer Title",
"type": "caption",
"payload": null,
"name": "Caption",
"font": null
},
{
"prov": [
{