Skip to content

Dev/add omnidocbench#4

Merged
cau-git merged 41 commits intomainfrom
dev/add-omnidocbench
Jan 7, 2025
Merged

Dev/add omnidocbench#4
cau-git merged 41 commits intomainfrom
dev/add-omnidocbench

Conversation

@PeterStaar-IBM
Copy link
Member

@PeterStaar-IBM PeterStaar-IBM commented Jan 1, 2025

No description provided.

@PeterStaar-IBM
adding the omnidocbench benchmarkl
b214077 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
added the table-parsing in omnidocbench
668b662 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
finished the OmniDocBench implementation
b3f1920 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
reformatted the code
3e5cee6 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
updated the README
e1bbd20 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
updated the README and the cli
8ef5c06 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
clean up the DP-Bench example
9f23cca 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
made the DPBench and OmniDocBench follow the same example code
cbce172 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
reformatted the code
34534b1 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
cleaned up the dp-bench create script
f83e44d 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
added the ability to see the clusters and reading order for layout
8a53826 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
reformatted the code
be04293 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
working on making datasets from pdf collections
50b517f 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
added the package_pdfs example
df7b307 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
added the FinTabNet-OTSL benchmark
7fbe411 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
reformatted the code
a1e9dd7 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
added the fintabnet example evaluation
b6bcc39 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
updated the README fort FinTabNet
a57832f 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
updated the README
1c33c50 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
refactored the table evaluations
f391788 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@cau-git cau-git requested review from cau-git and nikos-livathinos and removed request for cau-git and nikos-livathinos January 6, 2025 10:01
@PeterStaar-IBM
added the text inclusion in the table prediction
68d8d20 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
PeterStaar-IBM and others added 4 commits January 6, 2025 12:58
@PeterStaar-IBM
fixed the header of the HTML
b166973 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@PeterStaar-IBM
reformatted the code
291a594 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
@cau-git
fix: Formatting and unused code cleanup
5280851 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
chore: merge from remote
41b914c 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
nikos-livathinos
nikos-livathinos reviewed Jan 6, 2025
View reviewed changes
docling_eval/benchmarks/omnidocbench/create.py

assert len(true_page_images) == 1, "len(true_page_images)==1"

page_width = true_doc.pages[1].size.width
Copy link
Member

@nikos-livathinos nikos-livathinos Jan 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is there a reason why we check the second page and not the first one to get the page dimensions? What if the document has only one page?

Copy link
Member

@cau-git cau-git Jan 7, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the pages field is a map, not a list. The index should start with 1.

nikos-livathinos and others added 12 commits January 6, 2025 16:19
@nikos-livathinos
feat: Extend the CLI to create the OMNIDOCBENCH datasets for the layo…
f310d98 
…ut and tableformer modalities

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
@maxmnemonic
Added exit to benchmark end-to-end scripts in case git-lfs is not ins…
bba0d09 
…talled (#5)

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
@cau-git
fix: Use TableStructureModel from docling, use backends, fix bounding…
8f47099 
…box coordinates

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Merge branch 'dev/add-omnidocbench' of github.com:DS4SD/docling-eval …
e2c4e06 
…into dev/add-omnidocbench
@cau-git
Reinstate layout test on dpbench
16ab473 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Comments
663a295 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Comments
206ba9f 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Merge branch 'dev/add-omnidocbench' of github.com:DS4SD/docling-eval …
eaf204b 
…into dev/add-omnidocbench
@cau-git
Remove unused code
fedff46 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Remove more unused code
1c16a3d 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Fixes for Omnidoc
cf51d64 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Fixes for layout eval bounding boxes
7d111c1 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
cau-git
cau-git approved these changes Jan 7, 2025
View reviewed changes
docling_eval/benchmarks/omnidocbench/create.py

assert len(true_page_images) == 1, "len(true_page_images)==1"

page_width = true_doc.pages[1].size.width
Copy link
Member

@cau-git cau-git Jan 7, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the pages field is a map, not a list. The index should start with 1.

cau-git added 4 commits January 7, 2025 11:20
@cau-git
More fixes for OmniDoc, README updates
e2776f3 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
More fixes for OmniDoc, README updates
d16bcb0 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Replace git-lsf with HF snapshot_download
1f438dd 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git
Replace git-lsf with HF snapshot_download
0679cdc 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
@cau-git cau-git force-pushed the dev/add-omnidocbench branch from c2265f9 to 0679cdc Compare January 7, 2025 11:48
@cau-git cau-git merged commit 6bc9140 into main Jan 7, 2025
2 of 5 checks passed
@cau-git cau-git deleted the dev/add-omnidocbench branch January 7, 2025 11:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@nikos-livathinos nikos-livathinos nikos-livathinos left review comments

@cau-git cau-git cau-git approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@PeterStaar-IBM @cau-git @nikos-livathinos @maxmnemonic