first solution

.gitignore

@@ -1,154 +1,8 @@
-# ---> Python
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
 
+*~
+*.swp
+*.bak
+*.pyc
+*.o
+.DS_Store
+.token

README.md

@@ -1,2 +1,32 @@
-# book-layout
 
+Book layout
+==============================
+
+Detect structure of given page.
+
+Format
+------
+
+Each clipping found in a corresponding PDF/DjVu file. Each clipping should be given as L:P/X0,Y0,X1,Y1:PROB,
+where:
+
+    L — (optional) label
+    P — DjVu page number (starting from 1, optional if one-page documents are assumed)
+    X0, Y0, X1, Y1 — clipping coordinates (in pixels)
+    PROB — (optional) probability
+
+
+Directory structure
+-------------------
+
+* `README.md` — this file
+* `config.txt` — configuration file
+* `train/` — directory with training data
+* `train/in.tsv` — input data for the train set
+* `train/expected.tsv` — expected (reference) data for the train set
+* `dev-0/` — directory with dev (test) data
+* `dev-0/in.tsv` — input data for the dev set
+* `dev-0/expected.tsv` — expected (reference) data for the dev set
+* `test-A` — directory with test data
+* `test-A/in.tsv` — input data for the test set
+* `test-A/expected.tsv` — expected (reference) data for the test set

config.txt

@@ -0,0 +1 @@
+--metric Probabilistic-Soft2D-F1:N<F1> --metric Probabilistic-Soft2D-F0:N<P>P<2> --metric Probabilistic-Soft2D-F999999:N<R>P<2> --precision 4 -% --metric Probabilistic-Soft2D-{F1:N<F1>P<2>,F0:N<P>P<4>,F999999:N<R>P<4>}{t<Chapter:>N<Chapter>,t<Section:>N<Section>,t<Paragraph:>N<Paragraph>,t<Quote:>N<Quote>,t<Item:>N<Item>,t<Figure:>N<Figure>,t<P-continue:>N<P-continue>,t<Caption:>N<Caption>,t<Quote-con:>N<Quote-con>,t<Footnote:>N<Footnote>,t<Table:>N<Table>}

dev-0/expected.tsv

@@ -0,0 +1,27 @@
+Chapter:248,556,1149,641 Paragraph:99,704,1283,880 Paragraph:91,875,1283,1408 Paragraph:94,1409,1283,1737 Paragraph:91,1740,1283,2011
+Figure:299,184,1295,773 P-continue:170,800,1529,1628 Paragraph:170,1631,1503,2181 Paragraph:178,2186,1519,2286
+P-continue:268,208,1583,595 Paragraph:264,600,1583,756 Paragraph:257,820,1576,1726 Paragraph:264,1734,1579,2554
+Chapter:41,297,500,601 Paragraph:53,681,547,1672 Paragraph:53,1679,1563,2417 Figure:579,231,1538,1679
+Section:574,179,1259,298 Paragraph:253,309,1561,674 Paragraph:253,675,1561,1532 Paragraph:260,1529,1568,1999 Paragraph:257,1999,1565,2524
+Section:443,470,2120,689 Paragraph:160,705,2329,3356
+Section:630,2432,2094,2645 Section:742,481,1922,624 Paragraph:203,634,2495,2383 Paragraph:232,2645,2491,3677
+P-continue:249,216,1561,678 Paragraph:253,686,1561,1402 Paragraph:264,1406,1550,1723 Paragraph:253,1723,1565,2543
+Chapter:500,102,1862,624 Chapter:1971,92,3385,312 Section:2481,330,2876,402 Paragraph:1968,395,3375,1007 Paragraph:1975,1011,3361,1860 Paragraph:1968,1864,3361,2335
+P-continue:293,329,2195,898 Quote:297,912,2191,1155 Paragraph:297,1163,2199,2025 Paragraph:297,2033,2202,2484 Item:306,2512,935,2598 Item:304,2603,2204,2834 Item:301,2837,2201,3019 Item:306,3023,2198,3267
+Chapter:416,123,1813,229 Chapter:1972,120,3321,295 Paragraph:1952,313,3339,736 Paragraph:1955,740,3346,977 Paragraph:1959,981,3346,1135 Paragraph:1955,1132,3349,1882 Paragraph:1955,1883,3346,2185 Paragraph:1952,2186,3346,2303 Quote:413,344,1810,1951
+Chapter:296,590,1052,735 Paragraph:82,764,1274,980 Paragraph:85,984,1283,1329 Paragraph:85,1332,1292,1908 Paragraph:99,1917,1297,1979
+P-continue:148,159,1349,703 Paragraph:142,701,1349,991 Paragraph:145,995,1337,1591
+P-continue:133,481,2327,673 Paragraph:133,690,2327,1370 Section:487,1429,1948,1536 Paragraph:123,1531,2333,2714 Table:321,2725,2140,3608
+Quote:41,2086,1551,2335 Paragraph:25,1438,1554,1921 Paragraph:31,1258,1550,1425 Paragraph:31,1014,1550,1241 Paragraph:34,888,1544,1008 Paragraph:41,613,1554,881 Paragraph:37,202,1559,603
+Paragraph:201,192,1713,295 Paragraph:198,302,1707,519 Paragraph:198,525,1703,606 Paragraph:201,613,1703,691 Paragraph:204,702,1706,793 Paragraph:207,796,1716,969 Paragraph:204,969,1716,1142 Paragraph:201,1152,1716,1322 Paragraph:207,1331,1719,1422 Paragraph:201,1432,1722,1598 Paragraph:201,1605,1716,1734 Paragraph:198,1737,1707,1910 Paragraph:201,2052,1725,2222 Paragraph:201,2229,1716,2436
+Chapter:47,560,1275,757 Paragraph:55,778,1271,1373 Paragraph:57,1375,1260,1705 Paragraph:67,1708,1260,1990
+Section:846,723,1746,840 P-continue:182,444,2266,674 Paragraph:192,841,2281,1012 Item:594,1249,1756,1333 Item:600,1158,1762,1242 Item:600,1076,1762,1160 Item:636,1006,1901,1090 Paragraph:212,1330,2306,2556 Paragraph:216,2567,2279,2801 Item:234,3422,2275,3576 Paragraph:212,2820,2275,3399
+Paragraph:148,590,1332,912 Paragraph:145,915,1315,1405 Paragraph:142,1403,1320,1519 Paragraph:134,1523,1318,1965 Paragraph:151,148,1335,590
+P-continue:214,408,2307,1122 Paragraph:209,2197,2281,2442 Item:359,2447,1002,2520 Item:369,2531,1198,2591 Item:379,2594,2275,2740 Item:386,2748,2292,2871 Item:383,2874,2286,3020 Item:385,3584,1930,3651 Item:390,3434,2270,3576 Item:383,3364,1487,3434 Item:385,3151,2293,3363 Item:388,3023,2293,3145 Item:396,1127,1077,1193 Item:397,1199,1104,1263 Item:401,1267,1216,1333 Item:399,1338,2272,1466 Item:393,1476,2272,1608 Item:397,1613,2137,1685 Item:399,1687,2269,1896 Item:397,1905,1469,1967 Item:397,1969,2272,2099 Item:382,2104,1491,2182
+Paragraph:261,999,2399,1819 Paragraph:256,1819,2394,2464 Quote:487,2476,2015,2768 P-continue:261,502,2399,1004 Item:266,2787,2399,2931 Item:266,2937,2390,3272 Item:266,3279,2382,3487 Item:269,3490,2379,3640
+Paragraph:195,869,2252,2254 Paragraph:191,2263,2257,3326 Item:186,3360,2257,3569 P-continue:181,458,2242,859
+P-continue:286,320,2162,618 Quote:286,628,2167,1039 Paragraph:290,1043,2171,1337 Paragraph:290,1347,2166,1836 Quote:303,1853,2158,2225 Paragraph:303,2230,2158,2650 Paragraph:299,2659,2158,3157 Paragraph:294,3166,2157,3248
+Paragraph:535,455,2616,910 Paragraph:524,915,2610,2794 Paragraph:535,2794,2610,3158 Item:502,3206,2631,3586
+Paragraph:189,178,1548,480 Paragraph:199,484,1532,1081 Table:199,1202,1542,2004 Paragraph:205,2015,1551,2262 Caption:712,1092,1040,1186
+P-continue:467,114,1850,262 Paragraph:470,269,1850,670 Paragraph:473,674,1856,961 Paragraph:473,961,1860,1708 Paragraph:477,1711,1867,2281 Table:1957,511,3375,2299 Caption:2241,432,3071,504 P-continue:1944,107,3369,418
+Paragraph:266,912,2276,1983 Section:984,2014,1537,2121 Paragraph:256,2132,2297,3198 Paragraph:251,3193,2297,3628 P-continue:266,471,2286,896

dev-0/in.tsv

@@ -0,0 +1,27 @@
+przeglad_piechoty_12.png
+biologia_lekarska_6.png
+ognisko_nauczycielskie_5.png
+hejnal_10.png
+ognisko_nauczycielskie_29.png
+dudy_wielkopolskie_28.png
+dudy_wielkopolskie_26.png
+ognisko_nauczycielskie_18.png
+oswiata_i_wychowanie_14.png
+upadek_i_odrodzenie_szkol_jezuickich_141.png
+oswiata_i_wychowanie_6.png
+przeglad_piechoty_2.png
+przeglad_piechoty_3.png
+dudy_wielkopolskie_36.png
+hejnal_6.png
+hejnal_47.png
+przeglad_piechoty_4.png
+dudy_wielkopolskie_50.png
+przeglad_piechoty_17.png
+dudy_wielkopolskie_44.png
+dudy_wielkopolskie_16.png
+dudy_wielkopolskie_48.png
+upadek_i_odrodzenie_szkol_jezuickich_144.png
+dudy_wielkopolskie_37.png
+biologia_lekarska_24.png
+oswiata_i_wychowanie_12.png
+dudy_wielkopolskie_54.png

dev-0/out.tsv

@@ -0,0 +1,27 @@
+P-continue:151,478,1231,643 Paragraph:122,708,1282,884 Paragraph:89,1730,1279,2013 Paragraph:103,876,1276,1412 Paragraph:93,1415,1271,1760
+Quote:178,1645,1501,2172 Paragraph:172,2197,1553,2278 Paragraph:145,1646,1516,2186 Figure:216,174,1324,785 Paragraph:151,803,1525,1627
+P-continue:263,225,1547,588 Paragraph:245,225,1567,587 Paragraph:301,604,1510,744 Paragraph:252,1743,1574,2563 Paragraph:236,809,1587,1720
+Quote:55,237,502,588 Chapter:27,276,522,499 Paragraph:579,1324,1560,1688 Paragraph:45,2261,1566,2423 Paragraph:48,641,568,1655 Paragraph:40,1717,1555,2262
+Chapter:579,179,1285,281 Paragraph:237,2011,1567,2527 Paragraph:262,659,1559,1549 Paragraph:237,1536,1565,2012 Paragraph:245,291,1582,681
+P-continue:492,473,2016,703 Chapter:415,485,2053,701 Paragraph:162,742,2348,3395 Paragraph:202,3444,2325,3643
+Chapter:612,2431,2055,2618 Chapter:711,476,1936,619 Section:735,497,1926,619 Paragraph:211,632,2474,2401 Paragraph:210,2646,2466,3671
+Paragraph:253,1728,1557,2558 Paragraph:239,211,1562,680 Paragraph:249,1415,1560,1723 Paragraph:246,698,1562,1415
+Chapter:1974,120,3377,305 P-continue:499,122,1867,644 Paragraph:1966,1018,3363,1870 Paragraph:1950,1871,3408,2321 Paragraph:1958,395,3390,1005
+Paragraph:284,315,2257,900 P-continue:291,310,2189,902 Paragraph:360,2838,2184,3000 Paragraph:287,3007,2228,3274 Paragraph:365,2579,2181,2826 Paragraph:287,1166,2200,2024 Paragraph:295,2028,2222,2492 Paragraph:317,909,2168,1158
+P-continue:396,359,1805,1880 Paragraph:419,1699,1784,1946 P-continue:411,104,1724,304 Chapter:349,97,1819,331 Chapter:1976,110,3364,301 Quote:413,359,1808,1954 P-continue:1983,103,3329,315 Paragraph:1932,978,3338,1117 Paragraph:1957,2149,3340,2297 Paragraph:1959,723,3333,975 Paragraph:1955,1882,3354,2136 Paragraph:1940,1082,3366,1879 Paragraph:1952,317,3354,713
+Quote:272,566,1088,750 Paragraph:111,1915,1293,2009 Paragraph:101,1336,1286,1897 Paragraph:81,989,1286,1309 Paragraph:77,751,1274,976
+Paragraph:139,995,1339,1598 P-continue:148,156,1352,709 Paragraph:159,715,1333,986
+Quote:311,2836,1564,3549 P-continue:135,483,2299,671 Paragraph:152,677,2319,1381 Paragraph:129,1525,2317,2666
+Quote:46,2080,1543,2441 Paragraph:51,902,1516,1017 Paragraph:42,1059,1528,1251 Paragraph:25,1254,1539,1420 Paragraph:40,612,1555,889 Paragraph:51,196,1554,601 Paragraph:47,1434,1529,1934
+Paragraph:195,793,1728,1138 Paragraph:140,1161,1718,1348 Paragraph:203,529,1707,692 Paragraph:121,1304,1738,1419 Paragraph:205,1624,1704,1959 Paragraph:188,1408,1697,1654 Paragraph:203,272,1721,519 Paragraph:221,2002,1710,2233 Paragraph:193,2227,1731,2402
+Chapter:291,499,1031,569 Paragraph:72,574,1250,729 Paragraph:64,1714,1248,2004 Paragraph:60,776,1255,1377 Paragraph:70,1385,1251,1705
+P-continue:162,448,2295,712 Item:224,3426,2292,3595 Paragraph:226,2557,2240,2797 Paragraph:189,1331,2294,2541 Paragraph:219,2805,2257,3382
+Paragraph:135,1412,1317,1519 Paragraph:106,1529,1325,1984 Paragraph:128,161,1356,595 Paragraph:150,598,1336,920 Paragraph:130,931,1327,1409
+Item:403,2613,2213,2861 Paragraph:304,1653,2265,1906 Paragraph:224,1300,2346,1462 Item:339,2875,2329,3012 Paragraph:370,2603,2302,2876 Item:322,3579,2237,3678 Item:398,3389,2268,3565 Item:377,3159,2287,3348 Item:351,3014,2320,3145 P-continue:232,435,2272,1158
+Quote:224,2926,2366,3271 Item:244,2925,2397,3267 Item:345,2789,2404,2927 Paragraph:273,2924,2382,3268 Paragraph:423,2461,2222,2751 Item:268,3488,2396,3676 Item:290,3270,2383,3481 Paragraph:256,1004,2378,1808 P-continue:264,480,2413,1005 Paragraph:264,1812,2388,2444
+Item:189,3355,2292,3539 Paragraph:162,3358,2282,3534 Paragraph:202,851,2265,2230 P-continue:189,436,2263,876 Paragraph:188,2256,2261,3313
+Paragraph:278,3162,2163,3289 P-continue:302,310,2128,603 Paragraph:298,1855,2137,2210 Paragraph:311,1042,2130,1332 Paragraph:287,2663,2161,3145 Paragraph:298,619,2137,1046 Paragraph:293,2237,2164,2659 Paragraph:305,1346,2156,1835
+Quote:501,3218,2576,3578 Paragraph:495,3207,2596,3559 Item:529,3212,2602,3575 Paragraph:497,2797,2626,3157 Paragraph:537,459,2601,889 Paragraph:493,904,2626,2823
+Figure:1074,1201,1506,1929 Chapter:672,1111,1057,1180 Paragraph:198,2008,1557,2294 Paragraph:206,517,1561,1099 Paragraph:197,173,1559,468
+P-continue:459,109,1845,292 P-continue:1975,101,3329,428 Paragraph:476,271,1884,656 Paragraph:474,1706,1894,2287 Paragraph:479,660,1862,964 Paragraph:472,970,1871,1709
+Paragraph:259,3195,2299,3600 P-continue:274,459,2279,899 Paragraph:259,912,2291,1970 Paragraph:246,2111,2292,3181