units
units copied to clipboard
Dear authors: First of all, amazing work, and I enjoyed it a lot. Your paper stated: > In this ablation study, we use a hybrid transformer as a baseline >...
Dear authors, First of all, great work, and congratulations. Excited by your great work, I am interested in reproducing the training. From the paper, I understand there are `3` training...
  没有找到在转换lmbd格式时所需的具有poly等格式的json文件,希望您能提供一下,谢谢。
hi, 'Key Error' occurs when I go to the evaluation phrase. is there any other file needed? how should I fix this error? thank you! 
KeyError: 'e2e_method', when i run the commond "python contextualizer.py "
is it possible to train text recognition part by freezing the detection part training using only text recognition datasets? I want to improve the recognition part so please let me...
Hi, I have a question about training multiple detection formats jointly:Whether you choose a certain format like box or polygon to train the model in one training iter instead of...
Thanks for your great job! Is there any plan to release the code?
ModuleNotFoundError: Caught ModuleNotFoundError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/zys/miniconda3/envs/units/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/home/zys/miniconda3/envs/units/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data...