Alexander Rogachev

> > Now you can do: > > ```shell > # Finetuning > ./train.py pretrained=parseq # parseq-tiny, etc. See released weights > ``` How should the finetuning data be properly...

@bmusq have you changed any parameters like number of epochs or learning rate? Or did you just ran the train.py as is? And one more - did you use only...

@bmusq so, it is possible to finetune the model even changing the charset, right?

Should the training examples have some particular size or whether I'd better try to vary the resolution? Is it better to add images that only contain cropped text?

Is there a better way to process cases of multiple languages with same literals? Let's say that I want to fit a model with English and Greek words in the...

> Models in this repo were trained on 128x32 px images. > > > So, you mean vit, don't you? All the images are cropped and all the crops are...

Any solution so far?

Found an issue with the same error, but there were no solutions and updates. https://github.com/pytorch/pytorch/issues/78233