AdvancedLiterateMachinery
AdvancedLiterateMachinery copied to clipboard
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.
Hi, LORE model is great. I have a question, i saw the command in scripts infer have argument --nms but in file opts.py thís argument have action 'store_false'. It means...
Can i finetune LevOCR on my custom dataset for my language (Vietnamese) ?
作者您好,感谢作者release了这么好的工作,其中relation heads在提点方面有很大的作用,在modelscope上多语言的模型中没有relation heads部分的参数,如果不load relation heads直接训funsd,大概只能到70%+,relation heads部分的参数方便提供么?
when i use multiple gpus to train GeoLayoutLM, error as follows: Can't pickle local object 'linear_scheduler..lr_lambda' @wdp-007 @congyao @alibaba-oss Looking forward to your reply.
Now we have no reference function, please help me publish the model
I want to know how to proceed with key-value pairing only because I have label previously.
How can we pass more tokens than max_seq_length. I have more tokens than 512
I am interested in understanding whether GeoLayoutLM supports fine-tuning with QLoRa. I am not sure how to correctly configure this setup and would appreciate guidance on the matter. Thank you...
I am having difficulty understanding how GeoLayoutLM and VGT work together. The existing documentation does not seem to sufficiently explain the integration and collaboration of these components. - What is...