search

TongkunGuan / SIGA

[CVPR2023] Self-supervised Implicit Glyph Attention for Text Recognition
https://openaccess.thecvf.com/content/CVPR2023/papers/Guan_Self-Supervised_Implicit_Glyph_Attention_for_Text_Recognition_CVPR_2023_paper.pdf
103 stars 3 forks source link

Generate mask costs much time #2

Open bang123-box opened 11 months ago

bang123-box commented 11 months ago

hello: after reading your paper, I want to use the segment method to do some work also in the scene text recognition, but I find that at the training stage, to genergate the image mask cost much time, it will increase the training time. I first think to generate the mask at loacl machine but the Sythe dataset has 15M images it also will takes a lots of days to generate all the masks. so can I ask how you deal with the problem when you at the training.

TongkunGuan commented 11 months ago

We adopt parallel processing to generate the mask at the local machine.

bang123-box commented 11 months ago

thanks for answering me, but I did't find the parallel processing method to generate the mask at the local machine. Do you use the multiprocessing lib to achieve the parallel processing or other way？

TongkunGuan commented 9 months ago

We have added the mask generation codes.

We have added the mask generation codes.