You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I wanted to try SegNet, but I get the following error message. I supose it is because the file info.mat is missing. Could you please help me with that?
Error using DAGNetwork/calculatePredict>predictSingle (line 112)
Input network must not have batch normalization layers with empty Mean or Variance properties. To calculate
the batch normalization statistics, use the trainNetwork function.
Error in DAGNetwork/calculatePredict (line 13)
Y = predictSingle( ...
The text was updated successfully, but these errors were encountered:
Hi, I did a quick search and unfortunately I cannot find the info.mat file on my computer. It seems that I made a mistake and failed to copy it over from the machines the training was done on, which I unfortunately no longer have access to.
I will do a more careful search for it and will let you know if I find it. I apologize for this mistake.
Hi, thanks for your quick response. After reviewing more carefully I found that inside the file 'network.mat' there is a variable with the name 'info'. Perhaps that is why 'info.mat' was not included in the release 1.0.
However, I'm still having that error message. Now I think that it might be due to differences in Matlab versions. I'll keep looking for a solution and post here if I found one.
Hello, nice research!
I wanted to try SegNet, but I get the following error message. I supose it is because the file info.mat is missing. Could you please help me with that?
Error using DAGNetwork/calculatePredict>predictSingle (line 112)
Input network must not have batch normalization layers with empty Mean or Variance properties. To calculate
the batch normalization statistics, use the trainNetwork function.
Error in DAGNetwork/calculatePredict (line 13)
Y = predictSingle( ...
The text was updated successfully, but these errors were encountered: