{+7}zfxfB.%RWQ;6.:c0f?k}

Another option: pass the config **dict** to wandb.config, and let wandb update dict configs automatically ([ref](https://docs.wandb.ai/ref/python/init)). Two ways to do so: 1. pass cfg to WandbLoggerHook.before_run() (reference: #1773 ) ```python...

Thanks for the great works. Interested in `datasets.md` translation @gaotongxiao

> Hi @doem97 and @A465539338, complete guidance can now be found in the first post of this issue. Thanks! Great, received with thanks. Update soon.

@SeokjuLee Hi Dr. SeojkuLee, can you specify what is the data format with VP information in it? e.g. for no-VP, file list data format is like `VPGdata/000001.mat 3 536 184...

Or could you please show me any instance? only one sample image's label file is good.

same prob. Anyone has ideas? thanks

Sry made two pull requests =-=

Focal loss tested, not well. The cross-entropy and CE based methods are not suitable in this 2-classes problem.

> @SakuraRiven > 你好，使用直接训练好的EAST vgg模型，也不能复现性能，请问是什么问题呢？ > 我的LANMS模块从原作者里面的工程直接编译得到，应该没有影响吧. [https://github.com/argman/EAST/tree/master/lanms](url) Tensorflow version's implementation (via https://github.com/argman/EAST) has bugs. The author has fixed this bug in https://github.com/SakuraRiven/LANMS ,which should affect the results. Try SakuraRiven's...

Same here, MacOS, zsh shell, conda 23.7.2