AlibabaResearch/AdvancedLiterateMachinery

View on GitHub

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.

Stars: 1.8k
Forks: 195
Open beginner issues: 0
Indexed issues: 135

Dominant language: C++
License: Apache-2.0
Last GitHub push: Mar 17, 2026
Latest indexed: Sep 13, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Open All

135 open issues indexed

geolayout的modelscope上的中文模型 Open

AlibabaResearch/AdvancedLiterateMachinery#26 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
关于部署geoLayoutLM Open

AlibabaResearch/AdvancedLiterateMachinery#32 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Increase max_seq_length Open

AlibabaResearch/AdvancedLiterateMachinery#35 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
pairing of key value Open

AlibabaResearch/AdvancedLiterateMachinery#37 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
How to deploy the GeoLayoutLM model to modelscopes or huggingface? Open

AlibabaResearch/AdvancedLiterateMachinery#38 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
LevOCR on custom datasets Open

AlibabaResearch/AdvancedLiterateMachinery#44 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Can't pickle local object 'linear_scheduler.<locals>.lr_lambda' Open

AlibabaResearch/AdvancedLiterateMachinery#45 · 3 comments · 2 reactions · 0 assignees · Indexed Sep 13, 2026
About NMS merge output to avoid Overlap Cells? Open

AlibabaResearch/AdvancedLiterateMachinery#49 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
In Token classification, Is geolayoutlm using both entity extraction and entity linking Open

AlibabaResearch/AdvancedLiterateMachinery#51 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Does geolayoutlm offer any confidence scores for its token predictions in the token classification task? Open

AlibabaResearch/AdvancedLiterateMachinery#52 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
The "test_data_path" for LISTER Open

AlibabaResearch/AdvancedLiterateMachinery#54 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Is it possible to fine-tune Geolayout LM only for entity labelling ? Open

AlibabaResearch/AdvancedLiterateMachinery#55 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Use RE pretrained model(funsd dataset) Open

AlibabaResearch/AdvancedLiterateMachinery#56 · 2 comments · 3 reactions · 0 assignees · Indexed Sep 13, 2026
Problems with H1, H2, and H3 calculations in the code in the paper Open

AlibabaResearch/AdvancedLiterateMachinery#57 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Did you guys share the pretraining code Open

AlibabaResearch/AdvancedLiterateMachinery#58 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
能否公布VLPT-STD的测试代码和交叉注意力可视化代码？ Open

AlibabaResearch/AdvancedLiterateMachinery#60 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Final results' huge gap while using & not using pretrained weights? Open

AlibabaResearch/AdvancedLiterateMachinery#61 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Make cv_resnet50_ocr-detection-vlpt compatible for DocXchain Open

AlibabaResearch/AdvancedLiterateMachinery#63 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
some questions about embedding in the code and in the paper Open

AlibabaResearch/AdvancedLiterateMachinery#64 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
LORE wtw模型逻辑位置预测准确率问题 Open

AlibabaResearch/AdvancedLiterateMachinery#66 · 11 comments · 1 reaction · 0 assignees · Indexed Sep 13, 2026
Lister converges extremely slow Open

AlibabaResearch/AdvancedLiterateMachinery#67 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
DocMaster Open

AlibabaResearch/AdvancedLiterateMachinery#70 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
What the iou threshold in the F1 score of adjacency relationships is? Open

AlibabaResearch/AdvancedLiterateMachinery#71 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
如何调整batch_size，我的显存爆了 How to adjust batch_size, my video memory is full Open

AlibabaResearch/AdvancedLiterateMachinery#72 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Image Sizes and BBox Normalization Open

AlibabaResearch/AdvancedLiterateMachinery#73 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
在服务器上运行时，多卡不能正常运行（我租了3块，只有一块在使用中），如何解决 Open

AlibabaResearch/AdvancedLiterateMachinery#74 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
geolayoutLM中文的bbox应该选用什么级别的？ Open

AlibabaResearch/AdvancedLiterateMachinery#77 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
如何在自己的数据上训练？ Open

AlibabaResearch/AdvancedLiterateMachinery#81 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
processing of the pre-training dataset IIT CDIP 1.0 Open

AlibabaResearch/AdvancedLiterateMachinery#82 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
VGT模型配置中，VOCAB_SIZE也许应该为30522而不是30552 Open

AlibabaResearch/AdvancedLiterateMachinery#83 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 13, 2026
When will the pre-training code of GeoLayoutLM be released? Open

AlibabaResearch/AdvancedLiterateMachinery#86 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Conflicting license statements in VGT Open

AlibabaResearch/AdvancedLiterateMachinery#87 · 1 comment · 2 reactions · 0 assignees · Indexed Sep 13, 2026
Where do I load pre-trained DiT and GiT in the VGT code? Open

AlibabaResearch/AdvancedLiterateMachinery#89 · 5 comments · 1 reaction · 0 assignees · Indexed Sep 13, 2026
Get table from TSR model Open

AlibabaResearch/AdvancedLiterateMachinery#91 · 7 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
How to finetune DocXChain pretrained model "v1.2.0-docX-release/DocXLayout_231012.pth"? Open

AlibabaResearch/AdvancedLiterateMachinery#95 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
postprocessing of the result Open

AlibabaResearch/AdvancedLiterateMachinery#96 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
In VGT，how to generate a png image into a pkl format Grid image？？？ Open

AlibabaResearch/AdvancedLiterateMachinery#97 · 5 comments · 3 reactions · 0 assignees · Indexed Sep 13, 2026
How to make a data set in Funsd format? Open

AlibabaResearch/AdvancedLiterateMachinery#100 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
关于使用GeoLayoutLM推理一张图片。 Open

AlibabaResearch/AdvancedLiterateMachinery#101 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
BBOX shift towards top-left while finetuning the LORE model Open

AlibabaResearch/AdvancedLiterateMachinery#103 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
How can I train VGT? Open

AlibabaResearch/AdvancedLiterateMachinery#104 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
vgt能否识别中文版面？ Open

AlibabaResearch/AdvancedLiterateMachinery#107 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
LORE++ release Open

AlibabaResearch/AdvancedLiterateMachinery#109 · 2 comments · 10 reactions · 0 assignees · Indexed Sep 13, 2026
LORE-TSR can not build _ext extension Open

AlibabaResearch/AdvancedLiterateMachinery#112 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Export Geometric LayoutLM to ONNX Open

AlibabaResearch/AdvancedLiterateMachinery#114 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
LORE ONNX Export Open

AlibabaResearch/AdvancedLiterateMachinery#115 · 11 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Is there a quantized model for VGT/Doclaynet Open

AlibabaResearch/AdvancedLiterateMachinery#116 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Can MGP-STR deal with Chinese text? Can I train MGP-STR with Huggingface version? Open

AlibabaResearch/AdvancedLiterateMachinery#117 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Geolayoutlm, effect of image Open

AlibabaResearch/AdvancedLiterateMachinery#120 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
How to use the SER and RE pretrained models for inference on new file Open

AlibabaResearch/AdvancedLiterateMachinery#122 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026

AlibabaResearch/AdvancedLiterateMachinery

Get new issues in your inbox