Lei

let me check whether I still have them on the servers.

I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should...

Note that the evaluation codes in this repository are not very rigorous, as the prediction is performed on cropped images. It is suggested to first stitch the cropped masks, and...

> > I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the...

> > > > I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper,...

Hi, The division of the train, validation, and test set in the Potsdam is not the same in different papers. In my opinion, it is better to run the codes...

Hi, sorry that I forgot to reply. I am not sure what you talking about, the dataset is already split at the given link: https://rslab.disi.unitn.it/dataset/BLU/

Hi. Thank you for following this work. Please find the updated evaluation codes. Sorry that it is not well-organized and I do not have much time to optimize.

Hi, What's the model you used and what's the accuracy?

I just ran the codes again and did not see any problems. Here I provide a [link](https://drive.google.com/drive/folders/1zfRnJMT2ALVbDw6Eik5ZBiFk1QryFOFw?usp=sharing) to the trained model of SSCD-l+SCLoss.