Pluto caea73c8e3

Tables detection f1 (#3341) ...

This pull request add table detection metrics.

One case that was considered by me:

Case: Two tables are predicted and matched with one table in ground
truth
Question: Is this matching correct in both cases or just for on table

There are two subcases:
- table was predicted by OD as two sub tables (so half in two, there are
two non overlapping subtables) -> in my opinion both are correct
- it is false positive from tables matching script in
get_table_level_alignment -> 1 good, 1 wrong

As we don't have bounding boxes I followed the notebook calculation
script and assumed pessimistic, second subcase version

2024-07-08 13:29:52 +00:00

..

__init__.py

rfctr: prepare to add orig_elements serde (#2668)

2024-03-20 21:27:59 +00:00

test_element_type.py

bug: empty-elements (#1252)

2023-11-02 10:52:41 -05:00

test_evaluate.py

Tables detection f1 (#3341)

2024-07-08 13:29:52 +00:00

test_table_alignment.py

Fix not counting false negatives and false positives in table metrics (#3300)

2024-07-02 10:07:24 +00:00

test_table_detection_metrics.py

Tables detection f1 (#3341)

2024-07-08 13:29:52 +00:00

test_table_formats.py

Save table prediction in cells format (#2892)

2024-04-25 11:14:48 +00:00

test_table_structure.py

Fix not counting false negatives and false positives in table metrics (#3300)

2024-07-02 10:07:24 +00:00

test_text_extraction.py

feat: expose converters deckerd -> html and back (#3233)

2024-06-19 07:03:38 +00:00

test_utils.py

feat: update cct eval for text dir (#2299)

2024-01-05 23:34:53 +00:00