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

about training problem #9

Open
leizhu1989 opened this issue May 16, 2019 · 1 comment
Open

about training problem #9

leizhu1989 opened this issue May 16, 2019 · 1 comment

Comments

@leizhu1989
Copy link

I am sorry to bother you again.I have a problem in training ,it has error like:
I0516 15:40:50.364809 22238 net.cpp:129] Top shape: 1 1 48 64 (3072)
I0516 15:40:50.364815 22238 net.cpp:137] Memory required for data: 3158016
I0516 15:40:50.364820 22238 layer_factory.hpp:77] Creating layer conv1_1
I0516 15:40:50.364847 22238 net.cpp:84] Creating Layer conv1_1
I0516 15:40:50.364861 22238 net.cpp:406] conv1_1 <- data
I0516 15:40:50.364871 22238 net.cpp:380] conv1_1 -> conv1_1
F0516 15:40:50.366464 22244 data_layer.cpp:89] Check failed: this->transformed_data_.count()

I don't know why it is,I have check the shanghai data, my training picture size as same as yours 384x512 and density map size 48x64. In addition, I notice that your training data size 384x512, but test data size 704x1024, what is the reason, could you give me some ideas ,thank you very much

@leizhu1989
Copy link
Author

I have sovled the problem ,it can be trained now

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

1 participant