-
Hi @Somayeh-h,
Thank you for your interesting work. But I am really confused about the link you provided to the Nordland dataset [here](https://github.com/QVPR/VPRSNN/blob/modularSNN/non_modular_sn…
-
First of all, I would like to thank you for your work. However, when I was using it to process 1k images of 4k resolution, I noticed that the matching speed was very slow, around 3 pairs/s. I saw that…
-
Seeing the line [test_tokyo_best.py#L42](https://github.com/yxgeee/OpenIBL/blob/master/examples/test_tokyo_best.py#L42), the pretrained model is downloaded from the URL below.
https://github.com/…
-
Is it possible to convert to ONNX format? We want to work with TensorRT environment for runtime purpose.
-
Hello authors.
Thanks for making this work public. I just had a doubt. How are you doing testing exactly? is it like training on every train data (Pitts30k, MSLS, Robotcars, CMU seasons, etc) and t…
-
Hi,
I encountered this error assert self._parent_pid == os.getpid(), 'can only test a child process' when I run train.py with the MSLS dataset
-
Thanks a lot for your work about pytorch code.
When I tried to use the tokyo24/7 dataset, I found that the code could not run smoothly. I tried to look for the problem and found that the margin may b…
-
hi!
thank you for your excellent work! I run it successfully
now I want to make my own dataset and apply your work on it. Currenly I only get pictures of places, what else should I prepare for tr…
-
Hi,
I'm doing related research recently, how should I modify these codes If the backbone network is not vgg16
https://github.com/QVPR/Patch-NetVLAD/blob/main/patchnetvlad/models/local_matcher.py#L91…
-
Hello @Tobias-Fischer @StephenHausler ,I really appreciate for your work.
I have a question, the Supplementary Table 2 shows that the result of Extended CMU Seasons of Patch-NetVLAD:
Urban:19.2 / 48…