Arvind Rajan

Were you able to resolve this issue? @DhavalNiphade @anavc94 @argman @zxytim

Hi @anavc94, Thank you for sharing your findings. I agree with you, it is the nms part of the algorithm that is slowing things down. The more the texts in...

Hi @willi3by, Have you tried downgrading from CUDA 11.2 to CUDA 11.1? If you are using conda environment, following installation steps in https://www.tensorflow.org/install/pip, `conda install -c conda-forge cudatoolkit=11.1 cudatoolkit-dev=11.1 cudnn=8.1.0...

> What's typically done is a so-called "sliding window" approach, where you slide windows of 512 tokens across the document (for instance with a stride of 128 tokens). This means...

Hi all, I got it working for a longer sequence length. See https://github.com/microsoft/unilm/issues/942#issuecomment-1429033957. Thank you :)

Hi @superxii and @davelza95, I got it done using the implementation on `huggingface` library. These are the parameters that require tweaking to get LayoutLMv3 to work for a longer sequence...