Fix Dense init bug where initialisation of kernel weights with a numpy array raises a TypeError #3592
Conversation
This file contains hidden or 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
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Outdated suggestions cannot be applied.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.
Allow the initialisation of the kernel weight to be directly initialised by a numpy array, in line with the documentation of Dense layer.
Previously, before this amendment, there is a bug (#2913 ) where initialising kernel weight with numpy array raises
TypeError: in method 'random_initializer_with_rank', argument 1 of type 'CNTK::ParameterInitializer const &'This method of allowing dense kernel weight to be initialised by a numpy array is the same as what you see in the all the Convolution API Layers.