Simon-Stma

I am very interested in your work, when applying on fasterrcnn, I saw the margin padding for images with different resolutions (not divisible by patch_size) as you mentioned in the...

Questions about "RuntimeError: The size of tensor a (238) must match the size of tensor b (243) at non-singleton dimension 3"

1

In the summation of residual and identity, there is a dimensional mismatch, and after debugging, it is found that the dimensions will be different after transformer, how to solve this...

Thanks a lot!

Questions about how to use it for fasterrcnn which is based on detectron2.

1

Your work is very constructive. I see that the framework you are using for fasterrcnn based on mmdetection, so how do I migrate the code to 101x-C4 backbone for fasterrcnn...

question about augmentation policys on own dataset

1

If I use my own dataset (not a VOC-like natural image), should I re-search the new augmentation policy on my own dataset for optimal results?

Question about how to design dataset

1

I would like to ask again, my dataset has more small targets (remote sensing dataset), and the size difference between different objects is large (and after referring to the VOC...