RODNEY PETRUS BALANDONG

Thanks for the confirmation and detail explaination @gaotongxiao . May I know what happen if you use the pretrain 'pth' as a starting point for further training with the toydataset...

Hi @gaotongxiao , regarding my previous post, any update if the issue reproduceable at your local machine, if resume from availabe *pth*? Appreciate for the time 😃

Thanks for the update @gaotongxiao , appreciate it

I remember in one discussion which indicate `mmocr` prefer `jpg` than `png`

Hi @cvarun94 , you can refer this [Unofficial Notebook](https://github.com/balandongiv/mmocr_tutorial/blob/main/custom%20mmocr.ipynb). Note about the `repeat` also included in the `Notebook`

I am not that expert, but based from this [discussion](https://github.com/open-mmlab/mmocr/issues/1128#issuecomment-1171857679), I will definitely used the default `'DICT90'. Btw, Please ignore the `section` about `dict` in the Notebook. I used that...

> > > You are right, it looks like a typo and should be `raw` not `epochs` when you pass to `ica.fit`. Could you perhaps make a pull request to...

@jasmainak . Yes, I am more than happy to contribute.

Thanks for the feedback @xinke-wang .

Thanks for the package, it really usefull @vinsburg . Following to @Butler925 question, does this package allow more than multiple slices/group plotting?