diff --git "a/analysis.ipynb" "b/analysis.ipynb" --- "a/analysis.ipynb" +++ "b/analysis.ipynb" @@ -21,7 +21,7 @@ }, { "cell_type": "code", - "execution_count": 88, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -76,344 +76,11 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": { "id": "ZZD9JBaWa_T_" }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - " | document_image | \n", - "predicted_bboxes | \n", - "predicted_scores | \n", - "predicted_labels | \n", - "vectors | \n", - "weighted_vectors | \n", - "reduced_predicted_bboxes | \n", - "reduced_predicted_scores | \n", - "reduced_predicted_labels | \n", - "reduced_vectors | \n", - "reduced_weighted_vectors | \n", - "
---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", - "0.png | \n", - "[[29.3435668945, 643.4645996094, 739.842041015... | \n", - "[0.7836931944000001, 0.6475759149, 0.599450826... | \n", - "[Table, Table, Text, Section-header, Section-h... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[29.3435668945, 643.4645996094, 739.842041015... | \n", - "[0.7836931944000001, 0.6475759149, 0.599450826... | \n", - "[Table, Table, Text, Section-header, Section-h... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
1 | \n", - "1.png | \n", - "[[39.7452430725, 49.9780197144, 781.0, 602.479... | \n", - "[0.4839464724, 0.47660487890000003, 0.46349054... | \n", - "[Table, Text, Table, Table, Caption, Text, Tex... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[39.7452430725, 49.9780197144, 781.0, 602.479... | \n", - "[0.4839464724, 0.47660487890000003, 0.37839061... | \n", - "[Table, Text, Text, Text, Text, Text, Text, Te... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
2 | \n", - "2.png | \n", - "[[103.5238952637, 594.1181030273, 113.16088867... | \n", - "[0.7848277092, 0.7287962437000001, 0.709546744... | \n", - "[Title, Title, Table, Title, Title, Title, Tit... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[103.5238952637, 594.1181030273, 113.16088867... | \n", - "[0.7848277092, 0.7287962437000001, 0.709546744... | \n", - "[Title, Title, Table, Title, Title, Section-he... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
3 | \n", - "3.png | \n", - "[[88.863067627, 108.4031677246, 396.8055114746... | \n", - "[0.6572625637, 0.6462457776, 0.6340482235, 0.5... | \n", - "[Text, Text, Text, Picture, Text, Title, Text,... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[88.863067627, 108.4031677246, 396.8055114746... | \n", - "[0.6572625637, 0.6462457776, 0.6340482235, 0.5... | \n", - "[Text, Text, Text, Text, Title, Text, Text, Te... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
4 | \n", - "4.png | \n", - "[[82.0789871216, 45.9043922424, 709.9898071289... | \n", - "[0.8355703354, 0.6515532136000001, 0.562511444... | \n", - "[Table, Table, Title, Picture, Section-header,... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[82.0789871216, 45.9043922424, 709.9898071289... | \n", - "[0.8355703354, 0.5625114441, 0.1248187646] | \n", - "[Table, Title, Section-header] | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "... | \n", - "
19942 | \n", - "19942.png | \n", - "[[191.2108917236, 260.6972351074, 370.19641113... | \n", - "[0.6322918534, 0.5738079548, 0.541682004900000... | \n", - "[Text, Section-header, Text, Text, Text, Table... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[191.2108917236, 260.6972351074, 370.19641113... | \n", - "[0.6322918534, 0.5738079548, 0.448937684300000... | \n", - "[Text, Section-header, Text, Text, Table, Text... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
19943 | \n", - "19943.png | \n", - "[[256.7819213867, 81.0255050659, 392.073303222... | \n", - "[0.6657200456, 0.4550766945, 0.4131726623, 0.4... | \n", - "[Title, Text, Table, Text, Caption, Table, Pic... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[256.7819213867, 81.0255050659, 392.073303222... | \n", - "[0.6657200456, 0.4550766945, 0.4053039551, 0.3... | \n", - "[Title, Text, Text, Caption, Text, Title, Sect... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
19944 | \n", - "19944.png | \n", - "[[124.7773895264, 139.6303100586, 802.0, 658.7... | \n", - "[0.6754669547000001, 0.5447676778, 0.477854847... | \n", - "[Table, Page-footer, Page-footer, Table, Secti... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[124.7773895264, 139.6303100586, 802.0, 658.7... | \n", - "[0.6754669547000001, 0.5447676778, 0.477854847... | \n", - "[Table, Page-footer, Page-footer, Section-head... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
19945 | \n", - "19945.png | \n", - "[[14.6810312271, 343.2859802246, 736.022338867... | \n", - "[0.5109338164, 0.3732797503, 0.3711174726, 0.2... | \n", - "[Picture, Table, Text, Text, Text, Text, Table... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[14.6810312271, 343.2859802246, 736.022338867... | \n", - "[0.5109338164, 0.3711174726, 0.299810946, 0.20... | \n", - "[Picture, Text, Text, Text, Text, Text, Text, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
19946 | \n", - "19946.png | \n", - "[[26.7576179504, 270.6901855469, 751.377380371... | \n", - "[0.693007946, 0.3177033067, 0.2668364942, 0.26... | \n", - "[Table, Caption, Picture, Picture, Title, Titl... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[[26.7576179504, 270.6901855469, 751.377380371... | \n", - "[0.693007946, 0.3177033067, 0.2668364942, 0.25... | \n", - "[Table, Caption, Picture, Title, Title, Text, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... | \n", - "
19947 rows × 11 columns
\n", - "