wolfryu

how to load pretrained models

1

Thank you for your great job and share to us! Is there any way to load pretrained models from MhLiao/DB(https://github.com/MhLiao/DB)? I want to FT MhLiao/DB's models with my data.

hi Thank you for the excellent work and share!!! I just find that the remove link area process takes a lot of time to process: https://github.com/clovaai/CRAFT-pytorch/blob/e332dd8b718e291f51b66ff8f9ef2c98ee4474c8/craft_utils.py#L45 but, if link_threshold is...

训练数据和测试数据长度分布问题

2

感谢大佬的工作和分享！ 我下载了测试数据txt，发现全是10个字符的长度，训练数据没有下载，请问训练数据也全是10个字符长度吗？ 这样训练出来的模型会不会没法识别2，3个字符长度的文本？或者15，16个字符的文本？ 多谢！

识别效果简直太棒了！请问识别模型（CRNN）是怎么训练出来的？

4

至今为止见过最好的识别效果！ 请问CRNN是用哪个数据集训练出来的。有什么trick吗？多谢！

Request for get cross validation predict result y_foldN_pred

6

**Is your feature request related to a problem? Please describe.** when we do setup() like this: ~~~ task1 = setup(data = train_data, target = 'dead_or_not', test_data = unseen_data) clf =...

Thank you for your work and sharing! I am using rtx2080ti, is there anyway I can using better quality of VR mode? Thank you !