gxym / textbpn Goto Github PK

Thank you for your work.

I am confused about how did you sample the vertices from the predicted boundary proposals during the training in a learnable way ?

https://github.com/GXYM/TextBPN/blob/main/network/textnet.py#L74

It seems directly read from the input instead of from the predicted boundary proposal?

Thank you.

Hi, great works! I want to train TextBPN, but I can't find the train script. When will you provide train_textBPN.py file?

can not see train_textsnake.py script.

Hello, many thanks to your excellent work!

However, when I tried to use the pretrained model to evaluate total-text dataset, I found the name of pretrained model is "TextGraph_resnet50_550.pth" and it can not be successfully loaded to the model.

So I am wondering if there is anything wrong with the pretrained model?

hi, great works! But I can not find train_textBPN.py(I can find eval_textBPN.py). Can you provide this file?

I would appreciate your support in reproducing your results. I am trying, but I get zero true positive and zero average precision. Here is a screenshot.