MA CHENG

@ouguozhen i think my input is a lot of characters which have one specified font, the labels are the same characters which have different font . the model try to...

> > > Have u fix this problem? I'm current facing the same? > > > > > > delete some codes in finetune.py : model.state_dict = ( lambda self,...

@jackylee1 because models.rnn has been replaced by tf.contrib.rnn in new tensorflow version. but i have a similar issue . it shows ModuleNotFoundError: No module named 'copy_reg\r'. how can i deal...

> Hi, Thanks for your question. I'm unclear about the values presented in your table; could you please clarify what they represent? Additionally, I'd like to confirm whether you are...

> > Hi, Thanks for your question. I'm unclear about the values presented in your table; could you please clarify what they represent? Additionally, I'd like to confirm whether you...

> Thank you! do you know what is the minimal limit of the image size ratio?

> Hi, thanks for your work. I'm trying to test out the result of your work but found some difficulties on reproducing similar accuracy results. > > Below is the...

> > > Hi, thanks for your work. I'm trying to test out the result of your work but found some difficulties on reproducing similar accuracy results. > > >...

> I think using `datasets==1.14.0` is necessary in this case to get the model performance right. Maybe you can skip the version conflict for now? hi. when i set transfomers=4.17.0...

ALL RIGHT. I finally find the key of this problem: I test the princeton-nlp/CoFi-MRPC-s95, the result is the same as the ReadMe table mentioned.  by the way, here is...