Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Missing file: info.mat for SegNet #3

Open
dpbenalcazar opened this issue Aug 4, 2020 · 2 comments
Open

Missing file: info.mat for SegNet #3

dpbenalcazar opened this issue Aug 4, 2020 · 2 comments

Comments

@dpbenalcazar
Copy link

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( ...

@DanielKerrigan
Copy link
Collaborator

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.

@dpbenalcazar
Copy link
Author

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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants