zhubin

About the continued growth of CPU memory！

2

When I use GPU to train SWIN, the CPU memory keeps increasing, I want to ask what is going on? Is it a code bug? Very distressed this problem, hope...

Is the data size of the test fixed?

1

For example, the input of loftr is 480 x 480?

How do I add my own methods to test？

5

I copied the loftr code to add the required files, but when running my code failed: KeyError: 'block_type' Self. block_type = config['block_type'], which is the argument in my code

RuntimeError

8

RuntimeError: Tried to access nonexistent attribute or method '__call__' of type '__torch__.kornia.geometry.boxes.Boxes3D'. Did you forget to initialize an attribute in __init__()?: File "/home/szw/anaconda3/envs/image-matching-toolbox-main/lib/python3.7/site-packages/kornia/geometry/boxes.py", line 601 # Due to some torch.jit.script...

File "/home/szw/image-matching-toolbox-main/immatch/eval_inloc.py", line 5, in from third_party.hloc.hloc.localize_inloc import localize_with_matcher ImportError: cannot import name 'localize_with_matcher' 'localize_with_matcher' is not really in 'localize_inloc.py',Did you make a mistake?

fatal error: opencv2/imgcodecs/legacy/constants_c.h: 没有那个文件或目录 我用的是opencv3.4.6,请问下我运行官方版本是没有问题的，这该怎么去解决额？

How does Spatial MLP implement muti-head? I don't understand this, isn't this just a conv1d? Why does it say: use group convolution to implement multi-head MLP?

Does anyone tell me what the run command is? How to do the test? For example loftr test on inloc dataset