Added Adam Optimizer #28
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
* Update mod.rs * Update mod.rs
LazaroHurtado
requested changes
Apr 10, 2023
src/optimizers/adam.rs
Outdated
| grad += param.value() * self.weight_decay; | ||
|
|
||
| exp_avgs[i] = (beta1 * exp_avgs[i]) + ((1. - beta1) * grad); | ||
| exp_avg_sqs[i] = (beta2 * exp_avg_sqs[i]) + ((1. - beta2) * grad.pow(2)); |
There was a problem hiding this comment.
I believe you had to use num_traits::Pow because of the grad.pow(2) but you can do without the import by doing grad.powf(2.0)
There was a problem hiding this comment.
You're absolutely right, but the reason I did it is because RMSProp does use num_traits::Pow as well. I can go ahead and make the change to both, though!
* change pow to powf * Update adam.rs
Demba3
approved these changes
Apr 11, 2023
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Outdated suggestions cannot be applied.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.
Added
Adamstruct that implements theOptimizertrait, closely following its PyTorch implementation. It essentially combines the two types of momentums found inSGDandRMSProp(with respective decay rates β1 and β2) by keeping track of several gradient-based averages.Source: https://pytorch.org/docs/stable/generated/torch.optim.Adam.html#torch.optim.Adam