Xinyu Wang

> I also note that the text recognition accuracy also increases when resuming from a previous epoch without any changes of the training config, although loss increases. It seems that...

Thank you for the information. If possible, could you please provide the following info to help us to investigate the issue: 1. Did you modify any model structure or training...

> > Thank you for the information. If possible, could you please provide the following info to help us to investigate the issue: > > > > 1. Did you...

Hi, thank you for reporting the issues. We'll look into this as soon as possible. However, due to other high priority development schedules and the fact that we do not...

Hi, could you provide the training log so we can further explore the issue.

Hi, For training a text **detector** on datasets containing Chinese or other languages, it is not necessarily to modify too much of the configs. For example, IC17 (MLT) also contains...

Hi, it seems a bug caused by this PR https://github.com/open-mmlab/mmocr/pull/1119 , we'll fix this soon.

Hi, if you ONLY have rectangular annotations, you can get the pseudo `segmentation` label by `[x, y, x+w, y, x+w, y+h, x, y+h]`. However, if you already have quadrilateral or...

Hi, this error may caused due to [invalid polygonal bounding boxes](https://stackoverflow.com/questions/20833344/fix-invalid-polygon-in-shapely) with self-intersection included in the annotation of the dataset. If you are using [MMOCR 1.x version](https://github.com/open-mmlab/mmocr/tree/dev-1.x), you can directly...

Hi, 1.x is the latest major update that MMOCR has released, which introduces many new features (check our latest document for more details [English Doc](https://mmocr.readthedocs.io/en/dev-1.x/get_started/overview.html)/[Chinese Doc](https://mmocr.readthedocs.io/zh_CN/dev-1.x/get_started/overview.html)). The 0.x version (default...