maunzzz / cross-season-segmentation Goto Github PK

Hi Mans, the download link provided for the two correspondence datasets at visuallocalization.net seems no longer available;
and from my previous download, the 3dvis.ri.cmu.edu/data-sets/localization link is gone as well.
Could you provide a google drive or dropbox link to share the data you used for training? Thanks in advance!

Hi there, thanks a lot for your great work.

I took a look at the code, but I only found how to train the model (from train.py). I am wondering is it possible for you to provide a test.py file, using which we can test the segmentation performance of the given from-paper models.

Many thanks in advance!

Hi there, thanks a lot for your great work.

I took a look at the code, but I only found how to train the model (from train.py). I am wondering is it possible for you to provide a test.py file, using which we can test the segmentation performance of the given from-paper models.

Many thanks in advance!

Thanks for your great work! can you tell me how to get the image in the download_and_extract_images.sh file which is provided in https://www.visuallocalization.net/datasets/, because the website for the dataset http://3dvis.ri.cmu.edu/data-sets/localization/ is no longer available.

Hi there, thanks a lot for your great work.

I took a look at the code, but I only found how to train the model (from train.py). I am wondering is it possible for you to provide a test.py file, using which we can test the segmentation performance of the given from-paper models.

Many thanks in advance!

Hi,
I just can't save the dataset to my dropbox. "Saving to my dropbox" note appears, but it just don't work. I don't know whether the problem is Dropbox or the data. Any further instruction on how to download the dataset? Or can you please check the dataset again?

Thanks alot!

Hi there, thanks a lot for your great work.

I took a look at the code, but I only found how to train the model (from train.py). I am wondering is it possible for you to provide a test.py file, using which we can test the segmentation performance of the given from-paper models.

Many thanks in advance!