search

germain-hug / S2DHM

Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization (3DV 2019)
https://arxiv.org/abs/1907.03965
69 stars 15 forks source link

Running problem #3

Open VPRzhou opened 4 years ago

VPRzhou commented 4 years ago

Hi,I have a running question to consult you.When I do the command" python3 run.py --dataset cmu --mode sparse_to_dense",there is an error to arise.

Traceback (most recent call last): File "run.py", line 7, in from image_retrieval import rank_images File "/home/zhoul/S2DHM/s2dhm/image_retrieval/rank_images.py", line 6, in from datasets import base_dataset ImportError: cannot import name 'base_dataset' Could you tell me the reason.Thanks a lot.

germain-hug commented 4 years ago

Hi, Apologies for the delay, which version of Python are you using? It seems like this is a dependency issue, are you running the code from the s2dhm/ folder?

VPRzhou commented 4 years ago

Hi,the problem was solved.But I want reproduce the result of the sparse-to-dense matching approach using hypercolumn descriptors.Could you show me the process of matching code? Thank you a lot!

VPRzhou commented 4 years ago

sorry,another question I want to ask you.If I want to compare your method to some other methods,such as DELF、LF-Net and so on.How can I do the process of evalution of their performance on changing environments and draw a curve in the coordinate axis,what is the definition of X axis and Y axis?