Conversation
The data_transformer.cpp code crops centers according to the formula floor((image_dim - cropped_dim) / 2) However, the matlab code crops centers according to the formula: floor((image_dim - cropped_dim + 1) / 2) + 1 where the additional +1's are for matlab's indexing at 1. However, you only need one +1. Right now, this causes matcaffe to crop centers one pixel off from the data_transformer.cpp, which makes the extracted features different. I think you should remove one of the +1s so that matcaffe matches data_transformer.cpp exactly.
Member
|
Follow-up if this wasn't addressed by the new matcaffe in #2505. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The data_transformer.cpp code crops centers according to the formula
However, the matlab code crops centers according to the formula:
where the additional +1's are for matlab's indexing at 1. However, you only need one +1. Right now, this causes matcaffe to crop centers one pixel off from the data_transformer.cpp, which makes the extracted features different. I think you should remove one of the +1s so that matcaffe matches data_transformer.cpp exactly.