Add fast tanh and fast sigmoid to LSTM #43
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
sdatkinson
approved these changes
May 27, 2023
| @@ -32,6 +32,12 @@ inline float fast_tanh(const float x) | |||
| / (2.44506634652299f + (2.44506634652299f + x2) * fabsf(x + 0.814642734961073f * x * ax))); | |||
| } | |||
|
|
|||
| inline float fast_sigmoid(const float x) | |||
| { | |||
| return 0.5f * (fast_tanh(x * 0.5f) + 1.0f); | |||
| @@ -6,6 +6,8 @@ activations::ActivationHardTanh _HARD_TANH = activations::ActivationHardTanh(); | |||
| activations::ActivationReLU _RELU = activations::ActivationReLU(); | |||
| activations::ActivationSigmoid _SIGMOID = activations::ActivationSigmoid(); | |||
|
|
|||
| bool activations::Activation::using_fast_tanh = false; | |||
There was a problem hiding this comment.
I guess this is a separate but non-conflicting way to do this, then? FWIW, I think I'm happy to have it be global like this 👍🏻
There was a problem hiding this comment.
I guess this is a separate but non-conflicting way to do this, then?
Because the LSTM code calls the activation functions directly (since it is operating on individual weights), it needed a flag to key off of.
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Outdated suggestions cannot be applied.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.
This PR adds fast tanh and fast sigmoid activation for LSTM models. It keys off of the enable_fast_tanh()/disable_fast_tanh() methods.
My testing indicates around a 40% performance improvement for LSTM models.