We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? # to your account
Hi,
The current implementation of the marginal query (https://github.com/april-tools/cirkit/blob/fb4554c5e8b418611115d2c56538e5ac67cf31c4/cirkit/backend/torch/queries.py#L19C7-L19C21) integrates all samples in the minibatch for the same set of indices. Would it be possible to apply a different set of indices for each sample in the minibatch? For example, it would be nice to have an option to use a marginalization mask (with a size equal to the minibatch).
Best regards, Milan
The text was updated successfully, but these errors were encountered:
Hi Milan, thanks for suggesting this! We plan to support the marginalization mask for the next cirkit version.
Sorry, something went wrong.
andreasgrv
Successfully merging a pull request may close this issue.
Hi,
The current implementation of the marginal query (https://github.com/april-tools/cirkit/blob/fb4554c5e8b418611115d2c56538e5ac67cf31c4/cirkit/backend/torch/queries.py#L19C7-L19C21) integrates all samples in the minibatch for the same set of indices. Would it be possible to apply a different set of indices for each sample in the minibatch? For example, it would be nice to have an option to use a marginalization mask (with a size equal to the minibatch).
Best regards,
Milan
The text was updated successfully, but these errors were encountered: