Omar Moured

Large dataset and single image inference code

4

First of all, Thanks for the great work! I wanted to request if you can share minimal-PubLayNet or at least the code for **the inference on a single image as...

Thanks for the great tool. But I still have a problem installing it on WINDOWS 10. I downloaded Boost and build it using bootstrap. Then when compiling HDRView I get...

Flops and Param

1

Thanks for the work. Could you also add model complexity code such as the following: https://github.com/open-mmlab/mmsegmentation/blob/master/tools/get_flops.py Best, O.Moured

Thanks a lot for this contribution. It would be appreciated to also share the trained models from the paper or at least the high-performance ones such as ISTR. Best, Omar

why starting the "input" in base_prompt.py with two "\n"

1

Thanks for the great work. I have noticed in base_prompt.py [L121](https://github.com/luogen1996/LaVIN/blob/main/util/base_prompt.py#L121) that the input is added to "\n" so **it start with two "\n"**. Could you explain why?

Turn Off Saving Images in LMUData

1

When running experiments, encoded images from the TSV are automatically saved to the `LMUData` folder. Is there a way to skip saving them to optimize disk space usage? Would be...