Tsun Hin Cheung

You may consider the official repo to reproduce the result. I just notice that this repo is not the official implementation of the paper. The official repo is here: [https://github.com/MhLiao/DB](https://github.com/MhLiao/DB)....

I think I am having the same issue. I followed the commands in this repo and tried running build/app/qode.exe by doubling clicking it. However, there is nothing pop up on...

@nguyennm1024 My result is exactly the same as you: "hmean": 0.8181087597106885 with the dataset ICDAR 2015 and strong lexicon, where i used the default values in the evaluation/icdar2015/e2e/script.py and the...

os.makedirs("Process/data/Twitter15graph/",exist_ok=True)

1. Set the parameter device_map='auto' when load the LlamaForCausalLM.from_pretrained() 2. Replace the line in demo.py as: chat = Chat(model, vis_processor, device='cuda') It can run on two RTX 2080Ti in my...

> > Set the parameter device_map='auto' when load the LlamaForCausalLM.from_pretrained() > > Replace the line in demo.py as: chat = Chat(model, vis_processor, device='cuda') > > It can run on two...