sorourmo / 38-cloud-a-cloud-segmentation-dataset Goto Github PK

Sorry to disturb U , but i have a question that why the evaluatiion indicators in the "Cloud-net" and "Cloud_net++" are different. and could u share me the codes?

Hi, Sorour.
you said in your readme that the output of the mfile are an excel and a text file, and so how can we get the Entire Predicted Scenes image. When i run the mfile , it always tell me that the function can not be defined in the context, so i think it maybe the version of the Matlab does not match? So please tell me your Matlab version, thank you.

such as,
function out = QE_calcul (predict,gt, labels, conf_print)
out_both = cfmatrix(gt(:), predict(:), labels, 1, conf_print);

% We are interested in getting the numerical evaluators of "1" or
% "cloud" class only
ix = find(labels(:)==1);
out = out_both (ix,:); 

end

AND THE ERROR IS，
Error: File: evaluation.m Line: 1 Column: 1
Function definitions are not allowed in this context

Hi, thank you for great works.
I have a question. In your paper. you cropped 8000x8000 image into 384x384 patches and then resize them into 192x192. Why you did not directly crop image into 192x192 patches, it confused me. Thank in advance

Hi!

Whenever I start download, it continues for sometime and then fails. The behaviour is same when I download from work or home.
Would it be possible for you to upload it somewhere else, like google drive or some other cloud service?

Thanks!

I was looking through this dataset and noticed that many of the images are completely blank (all pixels are 0).
Using your mybatch_generator_prediction I loaded all the images and was surprised to find that roughly 1/3 of all the images – train and test alike – consist only of 0s

this is almost certainly inflating the kaggle statistics and is likely diluting the training process. Do you have any insight into what might be going on here?

For context: I downloaded the data from kaggle, in case that is relevant.