zhangh0920 issues

Repositories
Issues
Comments

Results 5 issues of


                                            zhangh0920

training issue

To train an implicit upsampler for a given image and backbone, how long does it take?

how to prepare ade20k? And how to inference the result on ade20k dataset?

about the flops

Are the M-adds you reported in your paper equivalent to FLOPs？

about training dataset

Could you please release the traing dataset? Thanks a lot!

Does VISORGPT supports to generate multiple instances with different sizes in an image?

I want to know if I want to generate objects with different sizes, such as a large building and lots of small windows in an image, can VISORGPT do it?