Enable minibatch processing #3
Merged
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
Note that we also reveres the order of sparse coding and ksvd_update Patch important bug with minibatch
RomeoV
force-pushed
the
minibatch-samples
branch
from
b4bfd08
to
e4c2fd2
Compare
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Outdated suggestions cannot be applied.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.
For large datasets, processing every sample takes a long time, but has diminishing returns.
We propose at each
ksvd_updatestep to only consider a subset of the samples, which are randomly chosen every time.The sparse coding stays the same.
We provide a new parameter
minibatch_sizewhich can be set tonothingto ignore this, or to a minibatch size.Since sparse coding still encodes every sample, the sparse coding time can start to dominate when small minibatches are chosen.