AdvancedLiterateMachinery

    A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

    Language: python

    Author: Daniel Payne (@danieldev)

    14 stars · 385 views

    Files

    • Applications (txt)
    • DocXChain (txt)
    • README.md (md)
    • modules (txt)
    • docbank_VGT_cascade_PTM.yaml (yaml)
    • doclaynet_VGT_cascade_PTM.yaml (yaml)
    • publaynet_VGT_cascade_PTM.yaml (yaml)
    • get_cache_file.py (py)
    • baselines_model (txt)
    • BART_vae_web_rendering.py (py)
    • vae.py (py)
    • train_wireless.sh (sh)
    • json_helper.py (py)
    • data_examples (txt)
    • ocr (txt)
    • tfjh0227_1.json (json)
    • xgpg0227_3.json (json)
    • tykp0227_18.json (json)
    • jggn0226_13.json (json)
    • rkww0217_1.json (json)
    • ysgj0223_88.json (json)
    • njxw0228_8.json (json)
    • qqgv0228_31.json (json)
    • kzlg0227_2.json (json)
    • ysxn0020_5.json (json)
    • phdg0023_7.json (json)
    • mgph0227_8.json (json)
    • yymg0227_1.json (json)
    • mywd0228_2.json (json)
    • gfhd0082_7.json (json)
    • xcuserdata (txt)
    • yixian.xcuserdatad (xcuserdatad)
    • xcschemes (txt)
    • xcdebugger (txt)
    • xcshareddata (txt)
    • xcschemes (txt)
    • ATTRIBUTION.md (markdown)
    • utils (txt)
    • detectors (txt)
    • external (txt)
    • OCR (txt)
    • LevOCR (txt)
    • figures (txt)
    • abinet (txt)
    • demo_imgs (txt)
    • levt (txt)
    • charset (txt)
    • LISTER (txt)
    • model (txt)
    • dataset (txt)
    • fig (txt)
    • config (txt)
    • LiteWeightOCR (txt)
    • figures (txt)
    • platform (txt)
    • IOS (txt)
    • formula_recognition.py (py)
    • output_formatting.py (py)
    • table_structure_recognition.py (py)
    • text_recognition.py (py)
    • file_loading.py (py)
    • text_detection.py (py)
    • layout_analysis.py (py)
    • resources (txt)
    • DocXChain_table_parsing_example.png (image)
    • DocXChain_text_reading_example.png (image)
    • DocXChain_formula_recognition_example.png (image)
    • requirements.txt (txt)
    • pipelines (txt)
    • table_parsing.py (py)
    • general_text_reading.py (py)
    • document_structurization.py (py)
    • utilities (txt)
    • visualization.py (py)
    • example.py (py)
    • LICENSE.md (md)
    • README.md (md)
    • resources (txt)
    • 关于参与申报2026年度湖北省科学技术奖项目公示情况的说明.jpg (image)
    • DuGuang.png (image)
    • lightweight_ios_demo_rst.png (image)
    • LICENSE (txt)
    • DocumentUnderstanding (txt)
    • VGT (txt)
    • object_detection (txt)
    • Configs (txt)
    • Base-RCNN-FPN.yaml (yaml)
    • cascade (txt)
    • D4LA_VGT_cascade_PTM.yaml (yaml)
    • testcuda.py (py)
    • testcpu.py (py)
    • inference.py (py)
    • pdf2img.py (py)
    • ditod (txt)
    • VGT.py (py)
    • config.py (py)
    • __init__.py (py)
    • Wordnn_embedding.py (py)
    • VGTcheckpointer.py (py)
    • tokenization_bros.py (py)
    • dataset_mapper.py (py)
    • FeatureMerge.py (py)
    • VGTbackbone.py (py)
    • VGTTrainer.py (py)
    • utils.py (py)
    • VGTbeit.py (py)
    • train_VGT.py (py)
    • create_grid_input.py (py)
    • README.md (md)
    • requirements.txt (txt)
    • figures (txt)
    • VGT_model.jpg (image)
    • LICENSE.md (md)
    • WebRPG (txt)
    • css_utils (txt)
    • color_process.py (py)
    • utils.py (py)
    • DuGuang_LiteOCR_IOS_DEMO (txt)
    • create_webrpg_data_split.py (py)
    • trainer_ar.py (py)
    • create_webrpg_data_1.py (py)
    • README.md (md)
    • test_sc.py (py)
    • requirements.txt (txt)
    • test_ele_iou.py (py)
    • run_tests.sh (sh)
    • dcn_v2.py (py)
    • hycv0228_3.json (json)
    • jkkw0023_1.json (json)
    • FID_model.py (py)
    • create_webrpg_data_2.py (py)
    • token_2_index.json (json)
    • LICENSE.md (md)
    • test_FID.py (py)
    • README.md (md)
    • GEM (txt)
    • README.md (md)
    • examples (txt)
    • fine_tuning (txt)
    • run_websrc (txt)
    • run.py (py)
    • run_swde (txt)
    • run.py (py)
    • LORE-TSR (txt)
    • README.md (md)
    • requirements.txt (txt)
    • input_images (txt)
    • wireless (txt)
    • wireless_sample2.png (image)
    • wireless_sample1.png (image)
    • wired (txt)
    • wired_sample2.jpg (image)
    • wired_sample1.jpg (image)
    • LICENSE.md (md)
    • src (txt)
    • eval.py (py)
    • lib (txt)
    • models (txt)
    • data_parallel.py (py)
    • model.py (py)
    • decode.py (py)
    • transformer.py (py)
    • scatter_gather.py (py)
    • classifier.py (py)
    • losses.py (py)
    • networks (txt)
    • resnet_dcn.py (py)
    • DCNv2_1.4 (4)
    • testcuda.py (py)
    • testcpu.py (py)
    • dcn_v2.py (py)
    • LICENSE (txt)
    • make.sh (sh)
    • src (txt)
    • datasets (txt)
    • sample (txt)
    • ctdet.py (py)
    • lycj0037_4.json (json)
    • dcn_v2.h (h)
    • cuda (txt)
    • dcn_v2_im2col_cuda.h (h)
    • vision.h (h)
    • cpu (txt)
    • vision.h (h)
    • dcn_v2_im2col_cpu.h (h)
    • dcn_v2_im2col_cpu.cpp (cpp)
    • dcn_v2_cpu.cpp (cpp)
    • dcn_v2_psroi_pooling_cpu.cpp (cpp)
    • vision.cpp (cpp)
    • setup.py (py)
    • dcn (txt)
    • __init__.py (py)
    • modules (txt)
    • dataset_factory.py (py)
    • dataset (txt)
    • deform_pool.py (py)
    • deform_conv.py (py)
    • functions (txt)
    • deform_pool.py (py)
    • deform_conv.py (py)
    • src (txt)
    • deform_pool_cuda.cpp (cpp)
    • deform_conv_cuda.cpp (cpp)
    • setup.py (py)
    • fpn_resnet.py (py)
    • dlav0.py (py)
    • fpn_mask_resnet.py (py)
    • fpn_resnet_half.py (py)
    • fpn_mask_resnet_half.py (py)
    • pose_dla_dcn.py (py)
    • DCNv2 (txt)
    • LICENSE (txt)
    • make.sh (sh)
    • src (txt)
    • dcn_v2.h (h)
    • cuda (txt)
    • dcn_v2_im2col_cuda.h (h)
    • vision.h (h)
    • cpu (txt)
    • vision.h (h)
    • dcn_v2_im2col_cpu.h (h)
    • dcn_v2_im2col_cpu.cpp (cpp)
    • dcn_v2_cpu.cpp (cpp)
    • dcn_v2_psroi_pooling_cpu.cpp (cpp)
    • vision.cpp (cpp)
    • setup.py (py)
    • utils.py (py)
    • utils (txt)
    • eval_utils.py (py)
    • oracle_utils.py (py)
    • image.py (py)
    • post_process.py (py)
    • adjacency.py (py)
    • debugger.py (py)
    • utils.py (py)
    • detectors (txt)
    • detector_factory.py (py)
    • base_detector.py (py)
    • ctdet.py (py)
    • trains (txt)
    • train_factory.py (py)
    • base_trainer.py (py)
    • ctdet.py (py)
    • table_small.py (py)
    • table.py (py)
    • table_mid.py (py)
    • external (txt)
    • Makefile (txt)
    • setup.py (py)
    • demo_wireless.sh (sh)
    • train (txt)
    • shapelyNMS.py (py)
    • logger.py (py)
    • opts.py (py)
    • eval.sh (sh)
    • main.py (py)
    • test.py (py)
    • scripts (txt)
    • infer (txt)
    • demo_test.sh (sh)
    • demo_wired.sh (sh)
    • train_wired.sh (sh)
    • demo.py (py)
    • _init_paths.py (py)
    • LayoutLLM (txt)
    • README.md (md)
    • LICENSE.md (md)
    • ProcTag (txt)
    • document_processor.py (py)
    • README.md (md)
    • main.py (py)
    • openai_integration.py (py)
    • znbx0223_7.json (json)
    • pjwg0227_1.json (json)
    • xrcy0227_73.json (json)
    • lzkg0078_15.json (json)
    • kzhb0228_4.json (json)
    • krcy0227_10.json (json)
    • lslw0227_37.json (json)
    • sgjc0228_14.json (json)
    • hsph0078_7.json (json)
    • prbf0004_1.json (json)
    • fsdh0226_1.json (json)
    • nrdb0228_2.json (json)
    • fnyf0227_1.json (json)
    • ftbd0003_1.json (json)
    • qgyk0226_2.json (json)
    • ssmd0217_1.json (json)
    • zjjw0023_1.json (json)
    • nrdb0228_3.json (json)
    • snml0226_1.json (json)
    • yjym0020_2.json (json)
    • xsph0078_1.json (json)
    • rllk0226_1.json (json)
    • kxnk0226_6.json (json)
    • tqlf0227_1.json (json)
    • xnyc0227_84.json (json)
    • qzlf0065_2.json (json)
    • qpyn0000_2.json (json)
    • lslw0227_45.json (json)
    • yjwd0227_6.json (json)
    • sljf0226_1.json (json)
    • kfhd0227_4.json (json)
    • pfhb0018_3.json (json)
    • gmlg0227_2.json (json)
    • jfgv0079_5.json (json)
    • lslw0227_39.json (json)
    • mkxx0023_1.json (json)
    • rlmg0227_14.json (json)
    • tykp0227_15.json (json)
    • xhfl0228_6.json (json)
    • htnk0226_6.json (json)
    • kzng0227_1.json (json)
    • rzld0217_6.json (json)
    • mjkk0226_1.json (json)
    • spwl0225_5.json (json)
    • jnjm0223_57.json (json)
    • xhgn0020_1.json (json)
    • fjbh0023_3.json (json)
    • hgjh0227_1.json (json)
    • fywn0226_21.json (json)
    • qmxd0227_2.json (json)
    • kycg0227_4.json (json)
    • qrwg0227_3.json (json)
    • mkhd0227_1.json (json)
    • pqcc0228_2.json (json)
    • qtnf0227_29.json (json)
    • qzpf0019_1.json (json)
    • rycg0227_1.json (json)
    • hmlg0227_9.json (json)
    • pmmw0023_3.json (json)
    • kkvx0227_1.json (json)
    • nfjx0023_1.json (json)
    • smwn0226_5.json (json)
    • shng0227_2.json (json)
    • nmph0227_1.json (json)
    • qnbx0227_1.json (json)
    • rxhm0227_11.json (json)
    • znyj0023_2.json (json)
    • symd0004_1.json (json)
    • zylf0227_1.json (json)
    • nskw0228_2.json (json)
    • tllg0227_13.json (json)
    • sjng0065_2.json (json)
    • nlcn0226_10.json (json)
    • lpcy0227_4.json (json)
    • zhph0227_9.json (json)
    • jrhl0226_4.json (json)
    • rxhm0227_12.json (json)
    • snyc0227_76.json (json)
    • xrcy0227_56.json (json)
    • nplf0227_10.json (json)
    • __init__.py (py)
    • DuGuang_LiteOCR_IOS_DEMO.xcodeproj (xcodeproj)
    • srfw0228_2.json (json)
    • ftmd0217_1.json (json)
    • geometry_utils.py (py)
    • space_layout.py (py)
    • LICENSE.md (md)
    • DocHieNet (txt)
    • README.md (md)
    • LICENSE.md (md)
    • GeoLayoutLM (txt)
    • utils (txt)
    • __init__.py (py)
    • bros (txt)
    • tokenization_bros_fast.py (py)
    • modeling_bros.py (py)
    • convnext.py (py)
    • detector_factory.py (py)
    • vision_model.py (py)
    • tokenization_bros.py (py)
    • transformer_local.py (py)
    • file_utils.py (py)
    • modeling_bros_convnext.py (py)
    • configuration_bros.py (py)
    • README.md (md)
    • model (txt)
    • __init__.py (py)
    • geolayoutlm_vie.py (py)
    • requirements.txt (txt)
    • train.py (py)
    • lightning_modules (txt)
    • geolayoutlm_vie_module.py (py)
    • data_modules (txt)
    • GeoLayoutLM_large_model_config.json (json)
    • DocXLayout (txt)
    • models (txt)
    • networks (txt)
    • vie_data_module.py (py)
    • vie_dataset.py (py)
    • bros_module.py (py)
    • schedulers.py (py)
    • fig (txt)
    • RFE heads.png (image)
    • LICENSE.md (md)
    • preprocess (txt)
    • funsd_el (txt)
    • configs (txt)
    • default.yaml (yaml)
    • GeoLayoutLM (txt)

    Loading code snippet…