Update cell.py for the problem when data_format='channels_first' #28
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for fixing this! How does Could you add |
I modify it for 1D, 2D and 3D data when using channels_first format.
|
Sorry, NCHW can not work with 1D or 3D convolutions. I correct this file again. |
|
My data is with shape of [50, 50, 50].I try to use the "bidirectional_dynamic_rnn" to deal with the indefinite length,and when the sequence_length is defined it shows that the reverse_op cannot handle the tensor with 6D. Is there any method to solve the bug? |
|
@1995Emma not sure, but perhaps this should be opened in a separate GitHub issue? Or is it related to @MissLikeWind's pull request? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
When the data_format is 'channels_first', there is a small problem. I solve it by modifying 'cell.py'.