AleRosae

Hi @NielsRogge, I also have a question about how the FUNSD dataset was made for LayoutLMv3. [Here](https://huggingface.co/datasets/nielsr/funsd-layoutlmv3/blob/main/funsd-layoutlmv3.py) I see how you retrieved the segment-level bounding boxes. But is there a...

Hi @zameelpichen, I do not know if the author is still interested in this project, but since I needed podcast data for a curricular project I tried to update the...

Hi @NielsRogge, are you planning to do one of your wonderful notebook tutorials once this PR is closed? I'm rather curios on how can we approach a token-classification task with...

Thank you for your answer @zinengtang! So if I'm not mistaking, to do so we should first normalize the original bounding boxes in range [0, 1000] on the basis of...

Hi @sromoam, for inference you can use the standard generate() method: ``` model = UdopForConditionalGeneration.from_pretrained("udop_model") outputs = model.generate(input_ids=input_ids, bbox=bbox, attention_mask=attention_mask, pixel_values=pixel_values, max_length=512, use_cache=False, num_beams=1, return_dict_in_generate=True) ``` You can obtain input_ids,...