Contrib/adamp #942
Contrib/adamp #942
Conversation
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
| class SGDP(Optimizer): | ||
| """Implements SGDP algorithm. | ||
|
|
||
| The SGDP variant was proposed in `Slowing Down the Weight Norm Increase in Momentum-based Optimizers`_. |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
E501 line too long (107 > 79 characters)
| class SGDP(Optimizer): | ||
| """Implements SGDP algorithm. | ||
|
|
||
| The SGDP variant was proposed in `Slowing Down the Weight Norm Increase in Momentum-based Optimizers`_. |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
W505 doc line too long (107 > 79 characters)
| https://arxiv.org/abs/2006.08217 | ||
| """ | ||
|
|
||
| def __init__( |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
D107 Missing docstring in init
| return perturb, wd | ||
|
|
||
| def step(self, closure=None): | ||
| """ |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
DAR201 Missing "Returns" in Docstring: - return
|
|
||
| import torch | ||
| import torch.nn.functional as F | ||
| from torch.optim.optimizer import Optimizer, required |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
F401 'torch.optim.optimizer.required' imported but unused
| running averages of gradient and its square (default: (0.9, 0.999)) | ||
| eps (float, optional): term added to the denominator to improve | ||
| numerical stability (default: 1e-8) | ||
| weight_decay (float, optional): weight decay coefficient (default: 1e-2) |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
W505 doc line too long (80 > 79 characters)
| wd_ratio (float): relative weight decay applied on scale-invariant | ||
| parameters compared to that applied on scale-variant parameters | ||
| (default: 0.1) | ||
| nesterov (boolean, optional): enables Nesterov momentum (default: False) |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
E501 line too long (80 > 79 characters)
| wd_ratio (float): relative weight decay applied on scale-invariant | ||
| parameters compared to that applied on scale-variant parameters | ||
| (default: 0.1) | ||
| nesterov (boolean, optional): enables Nesterov momentum (default: False) |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
W505 doc line too long (80 > 79 characters)
| https://arxiv.org/abs/2006.08217 | ||
| """ | ||
|
|
||
| def __init__( |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
D107 Missing docstring in init
| return perturb, wd | ||
|
|
||
| def step(self, closure=None): | ||
| """ |
There was a problem hiding this comment.
[pep8] reported by reviewdog 🐶
DAR201 Missing "Returns" in Docstring: - return
Before submitting
catalyst-make-codestyle && catalyst-check-codestyle(pip install -U catalyst-codestyle).make check-docs?Description
Related Issue
Type of Change
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.