mirror of
https://github.com/docling-project/docling-eval.git
synced 2026-05-17 13:10:47 +00:00
Nikos Livathinos
8dee74c09f
* fix: Many code refactorings to support TableFormerMode (by default ACCURATE). Additonally: - Clean up the overall implementation of TableFormerUpdater and set the AcceleratorOptions. - Extend CLI to allow the creation of table datasets (PTN, FTN, P1M). Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * docs: WIP: Updating the Readme with benchmarks for the FTN, PTN, P1M. Move the DP-Bench and OmniDocBench in separate files inside docs/ and provide links in Readme Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * docs: Add evaluation files inside docs/ with json/png files for FTN, PTN, P1M Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * docs: Fix the images links for DP-Bench, OmniDocBench docs Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * docs: Refactor the Readme to have evaluation data and results for the table datasets FTN, PTN, Pub1M Add code snippets how to run the evalutions and visualizations for all datasets. Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> * docs: Fix broken links in Readme Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com> --------- Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
26 lines
1.6 KiB
Plaintext
26 lines
1.6 KiB
Plaintext
FinTabNet tableformer TEDS_struct-only:
|
|
|
|
mean=0.90 median=0.92 std=0.09
|
|
|
|
| TEDS_struct-only | prob [%] | acc [%] | 1-acc [%] | total |
|
|
|--------------------|------------|-----------|-------------|---------|
|
|
| (0.000, 0.050] | 0 | 0 | 100 | 0 |
|
|
| (0.050, 0.100] | 0 | 0 | 100 | 0 |
|
|
| (0.100, 0.150] | 0 | 0 | 100 | 0 |
|
|
| (0.150, 0.200] | 0.1 | 0 | 100 | 1 |
|
|
| (0.200, 0.250] | 0.1 | 0.1 | 99.9 | 1 |
|
|
| (0.250, 0.300] | 0 | 0.2 | 99.8 | 0 |
|
|
| (0.300, 0.350] | 0 | 0.2 | 99.8 | 0 |
|
|
| (0.350, 0.400] | 0 | 0.2 | 99.8 | 0 |
|
|
| (0.400, 0.450] | 0.2 | 0.2 | 99.8 | 2 |
|
|
| (0.450, 0.500] | 0.1 | 0.4 | 99.6 | 1 |
|
|
| (0.500, 0.550] | 0.6 | 0.5 | 99.5 | 6 |
|
|
| (0.550, 0.600] | 0.6 | 1.1 | 98.9 | 6 |
|
|
| (0.600, 0.650] | 0.6 | 1.7 | 98.3 | 6 |
|
|
| (0.650, 0.700] | 0.8 | 2.3 | 97.7 | 8 |
|
|
| (0.700, 0.750] | 1.2 | 3.1 | 96.9 | 12 |
|
|
| (0.750, 0.800] | 3.7 | 4.3 | 95.7 | 37 |
|
|
| (0.800, 0.850] | 14.3 | 8 | 92 | 143 |
|
|
| (0.850, 0.900] | 18.9 | 22.3 | 77.7 | 189 |
|
|
| (0.900, 0.950] | 30.8 | 41.2 | 58.8 | 308 |
|
|
| (0.950, 1.000] | 28 | 72 | 28 | 280 | |