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
Hello.
Thank you for presenting your excellent research.
I have a question about pre_seq_length.
I have tried the SimVP in the Colab tutorial.
When I set pre_seq_length = 10 and aft_seq_length = 20, it ran fine. However, when I changed pre_seq_length to pre_seq_length = 5 or 20, I got the error “running_mean should contain 320 elements not 640”. I found that the number of channels in the batch normalization layer is not appropriate. I would like to know how to solve this problem, can I make pre_seq_length variable?
What is the solution? Is the only way to change the structure of the model?
Thank you in advance for your help.
The text was updated successfully, but these errors were encountered:
Hello.
Thank you for presenting your excellent research.
I have a question about pre_seq_length.
I have tried the SimVP in the Colab tutorial.
When I set pre_seq_length = 10 and aft_seq_length = 20, it ran fine. However, when I changed pre_seq_length to pre_seq_length = 5 or 20, I got the error “running_mean should contain 320 elements not 640”. I found that the number of channels in the batch normalization layer is not appropriate. I would like to know how to solve this problem, can I make pre_seq_length variable?
What is the solution? Is the only way to change the structure of the model?
Thank you in advance for your help.
The text was updated successfully, but these errors were encountered: