search

cvlab-stonybrook / PaperEdge

The code and the DIW dataset for "Learning From Documents in the Wild to Improve Document Unwarping" (SIGGRAPH 2022)
MIT License
121 stars 23 forks source link

could you please offer more info for rookies like me to run the code? #4

Open 1benwu1 opened 2 years ago

1benwu1 commented 2 years ago

i'm new to deep learning and recently i become recently interested in paper dewarping. i've read some papers from your lab. i'm eager to test your amazing work on my pc. but i really don't know how to run the code.... so could you please offer me more guidance or write something down in the readme

wkema commented 2 years ago

Sorry for the late reply and it was my bad I did not add a more detailed instruction in the README page, and thank you for your interest in my work:)

Unfortunately I might not have more time working on this. Moreover, if you are totally new to deep learning, the topic in this repo might be a little advanced for you. You might want to start with some simpler and well-maintained repos first and get yourself familiar with the pipeline then revisit this repo. You may want to check the eval.py file which is pretty self-contained for inference.

I noticed some users have successfully used my code and models...hopefully they could contribute a better README lol.

1benwu1 commented 2 years ago

Sorry for the late reply and it was my bad I did not add a more detailed instruction in the README page, and thank you for your interest in my work:)

Unfortunately I might not have more time working on this. Moreover, if you are totally new to deep learning, the topic in this repo might be a little advanced for you. You might want to start with some simpler and well-maintained repos first and get yourself familiar with the pipeline then revisit this repo. You may want to check the eval.py file which is pretty self-contained for inference.

I noticed some users have successfully used my code and models...hopefully they could contribute a better README lol.

it's good to receive your reply. actually, i ain't totally new to DL, well but i'm a real rookie. my pro was that when i try to run eval.py i found it doesn't work well. i thought it was the visdom library cuz i've never used it before. however, later i found out that my directories was wrong... so my pro was solved. anyway, thank you so much for your reply and i really like your fantastic works from docU to paperedge which inspire me a lot

wkema commented 2 years ago

Sorry for the late reply and it was my bad I did not add a more detailed instruction in the README page, and thank you for your interest in my work:) Unfortunately I might not have more time working on this. Moreover, if you are totally new to deep learning, the topic in this repo might be a little advanced for you. You might want to start with some simpler and well-maintained repos first and get yourself familiar with the pipeline then revisit this repo. You may want to check the eval.py file which is pretty self-contained for inference. I noticed some users have successfully used my code and models...hopefully they could contribute a better README lol.

it's good to receive your reply. actually, i ain't totally new to DL, well but i'm a real rookie. my pro was that when i try to run eval.py i found it doesn't work well. i thought it was the visdom library cuz i've never used it before. however, later i found out that my directories was wrong... so my pro was solved. anyway, thank you so much for your reply and i really like your fantastic works from docU to paperedge which inspire me a lot

oh sorry I misunderstood your previous message.

Yeah visdom had some issues at that time and that repo was later took over by another group I think. I am not sure about its current status now. I actually still had an open issue in that repo lol https://github.com/fossasia/visdom/issues/735

For the worst case scenario, you may want to get rid of all the visdom related code and replace it with other visualization tool like matplotlib or so.

zbzzz commented 2 years ago

Dear author, I am a novice in deep learning, and I have been asked to run the code recently. I would like to ask you how to run this code warehouse, how to modify directory files, and where to store data sets. Thank you in advance

erenxjw commented 1 year ago

Hello everyone, I hope you can share with me the code of the training process of the two pre-models in the code, it can be of great help to me, I want to learn how to train the two pre-models by myself. My email is erenxjw@163.com