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.
请问使用resnet作为骨干,freeze_bn该如何设置呢
Hi, thank you for your great work! I’m interested in training the GeoLayoutLM model with just one RE head. Could you share if this could be done with a simple...
运行train.py时override抛出了TypeError: VIEDataModule.train_dataloader: return type `None` is not a `typing.这个错误,应该是在导入包时就出现的,可是此时数据还未加载,肯定会返回None,这该如何解决呢? 还是我的数据集布置有问题呢? 求大佬们解答/(ㄒoㄒ)/~~
Hello, Thank you for your work on GEM. I noticed in the paper that there was a mention of plans to release the pretraining code. Any update on this would...
I can see no code or guide on how to use OmniParser for local files for visual inspection, not eval. Is there anybody who's done that? Thanks.
Hi, Thank you for creating and sharing the Vision Grid Transformer repository. I am currently trying to evaluate the model on the DocLayNet test dataset in order to replicate the...
Hello, author, thank you for your open source work. I would like to ask about the TRCG part of SceneVTG, which uses an MLLM and the input dialogue is very...
wh labels计算的是: wh[k] = ct[0] - 1. * CorNer[0], ct[1] - 1. * CorNer[1], \ ct[0] - 1. * CorNer[2], ct[1] - 1. * CorNer[3], \ ct[0] - 1. *...