Use batches for SmoothGrad #78
Open
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
gkapish
reviewed
May 12, 2022
Contributor
gkapish
left a comment
gkapish
left a comment
There was a problem hiding this comment.
@lenbrocki, thanks you for the pull request. The proposed GetSmoothedMask() implementation assumes that GetMask() of every saliency method can accept a batch of images. Unfortunately, it is not the case currently. Note, that SmoothGrad can be applied not only on vanilla gradients method but on other methods too.
| grad = self.GetMask(x_plus_noise, call_model_function, call_model_args, | ||
| shape = (nsamples,) + x_value.shape | ||
| noisy_samples = np.zeros(shape) | ||
| for i in range(nsamples): |
Contributor
There was a problem hiding this comment.
You could get rid of the loop completely if you used np.repeat(...) and generating the noise mask for the batched shape.
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Outdated suggestions cannot be applied.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.
To speed up the computation for obtaining smoothed masks, the noisy samples are created first and gradients are obtained as a single batch for all the noisy samples. Afterwards the gradients (or their squares) are summed to give the final smoothed mask.