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

Some errors I meet in the training #57

Open
1348205 opened this issue Sep 6, 2018 · 2 comments
Open

Some errors I meet in the training #57

1348205 opened this issue Sep 6, 2018 · 2 comments

Comments

@1348205
Copy link

1348205 commented Sep 6, 2018

Check failed: 2 == this->num_spatial_axes_ (2 vs. 3) CuDNNConvolution input must have 2 spatial axes (e.g., height and width). Use 'engine: CAFFE' for general ND convolution.
*** Check failure stack trace: ***

Hi, I check several possibilities for the error, and also try use only cpu, but the error is still exist. Can you some suggestions for this error, Thank you very much

@1348205
Copy link
Author

1348205 commented Sep 6, 2018

cudnn_conv_layer.cpp:94] Check failed: 2 == this->num_spatial_axes_ (2 vs. 3) CuDNNConvolution input must have 2 spatial axes (e.g., height and width). Use 'engine: CAFFE' for general ND convolution.
*** Check failure stack trace: ***

This is the whole error statement

@HainKUL
Copy link

HainKUL commented Feb 18, 2019

Hi, I also encountered the same problem. did you solve it finally?

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