red thing

@slava-vishnyakov I looked at your github action and it is failing?

Here is some more info on the crash: ``` * thread #1, queue = 'com.apple.main-thread', stop reason = EXC_BAD_ACCESS (code=1, address=0x1) frame #0: 0x00000001003b6cd8 realesrgan-ncnn-vulkan`___lldb_unnamed_symbol11335 + 172 realesrgan-ncnn-vulkan`___lldb_unnamed_symbol11335: -> 0x1003b6cd8...

Same issue.

Me too.

This would be awesome.

> @redthing1 Thank you for reproducing the results on the DocVQA dataset. I also agree to want to do this work. Can you provide the scripts transcriptions？ Thank you ver...

I keep getting emails about people asking for my MSRead OCR processed dataset. So for everyone's sake I will upload it for you all in the next few days.

You will have to use my training scripts here because this is preprocessed data in ARROW format: https://github.com/redthing1/layoutlm_experiments#2-train-on-docvqa-data But if you want you can convert it back. I've run everything...

Dataset archives: https://github.com/redthing1/layoutlm_experiments/releases/download/v0.1.0/docvqa_proc_20220808.tar.zst This includes MSRead processed data, in both formats of seq2seq and extractive formulation. You can load with my script (which uses HF datasets) and convert it to...

I don't have the test data 😂 it is not released for obvious reasons.