Geewook Kim

Close this issue since it seems to be resolved :) Feel free to reopen this or open another issue if you have anything new for sharing or debugging.

Hi, this issue is related to the `window_size` of the image encoder (swin). For `donut-base`, set the size of each axis to a multiple of 320, e.g., [640, 640], [960,...

Hi @David-McSharry, thank you for bringing this issue to our attention. We have received multiple reports regarding challenges in configuring the testing environment for `donut-python` due to recent updates in...

Hi @Vadkoz, The current trainer removes `state_dict` in the ckpt files (check https://github.com/clovaai/donut/blob/1.0.9/train.py#L29-L31). However, it saves the model weights in HF's transformers format (check https://github.com/clovaai/donut/blob/1.0.9/lightning_module.py#L146-L150). To load the model weights,...

Hi @csanadpoda , yes, we used fp16 ( https://github.com/clovaai/donut/blob/master/train.py#L127 ). Hope this helps ;)

Hi @csanadpoda, I guess this issue might be caused by not cloning the official branch of the repo. Here's the link: https://huggingface.co/naver-clova-ix/donut-base-finetuned-cord-v1/tree/official Please let me know if you are still...

Hi @YuanEZhou , this might be helpful to you: - https://github.com/clovaai/donut/issues/23 Best.

Hi, thank you for your interest on our work :) Let me get a quick/short answer first -> Yes, it would be possible by removing unnecessary tokens in the vocabulary...

I think there are many options to implement this feature. First one is to remove unnecessary tokens in the vocabulary. For this, you should update vocabulary of the tokenizer and...

Hi, thank you for bringing this issue to our attention. It appears that the problem is likely related to the environment configuration. We will resolve this issue, while also updating...