Closed digantamisra98 closed 3 years ago
@digantamisra98 thnx for letting us know! we are eagerly waiting for a PR to have this in!
@vigsterkr sure. Thanks. I or my colleague will try to put up a PR in the next few days. Thanks for the consideration.
Hi. Is this still open?
@ashutosh-b-b yes, the PR is up - https://github.com/shogun-toolbox/shogun/pull/4812
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
.
Thank you, I'll get back on this.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
This issue is now being closed due to a lack of activity. Feel free to reopen it.
Mish is a new novel activation function proposed in this paper. It has shown promising results so far and has been adopted in several packages including:
All benchmarks, analysis and links to official package implementations can be found in this repository
It would be nice to have Mish as an option within the activation function group.
This is the comparison of Mish with other conventional activation functions in a SEResNet-50 for CIFAR-10: (Better accuracy and faster than GELU)