Problem 15 1D Convolution: Fix convolution inconsistencies#7
Open
spatters wants to merge 1 commit intosrush:mainfrom
Open
Problem 15 1D Convolution: Fix convolution inconsistencies#7spatters wants to merge 1 commit intosrush:mainfrom
spatters wants to merge 1 commit intosrush:mainfrom
Conversation
… f to call np.correlate rather than np.convolve as convolve fips y before applying which is not the standard definition in deep learning. In the current question the indexing for y and the f definition are inconsistent, so either need to change the function as I have done, or flip the y indices in the formula.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
There are two problems with the convolution definition in problem 15
jindex should run from 0 to K-1. I have corrected this.fcallsnp.convolvewhich flips y before applying the convolution. So the function behavior is inconsistent with indexing in the convolution definition. Can either change the definition or changefto usenp.correlatewhich does not flip. I have done the latter as I think not flipping is the standard in deep learning.