Liang Qiao

> 可以试一下在配置config中手动指定一下中用到这个.so文件的绝对路径，GPMADataGeneration模块中修改的lib_name和lib_dir

We have only published the model trained on PubTabNet, you may use the same code the train the model on ICDAR2013 or other datasets.

Some of the parameters you mentioned are actually un likely to have a big impact on the performance of the model. It is usually caused by a possible problem with...

> The quatity of IC13 images is very small, so the model should be converged (or even over-fitted) easily. You may train the dataset for a larger epoch to see...

> Also, for fine tuning, I set "load_from=" in lgpma_base.py to the publicly available maskrcnn-lgpma-pub-e12-pub.pth, is that correct? Not setting it to "resume_from". yes

@jianghui11hik