Shortcuts

import math
import torch
from .optimizer import Optimizer

The original Adam algorithm was proposed in Adam: A Method for Stochastic Optimization_.
The AdamW variant was proposed in Decoupled Weight Decay Regularization_.

Arguments:
params (iterable): iterable of parameters to optimize or dicts defining
parameter groups
lr (float, optional): learning rate (default: 1e-3)
betas (Tuple[float, float], optional): coefficients used for computing
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)
algorithm from the paper On the Convergence of Adam and Beyond_
(default: False)

.. _Adam\: A Method for Stochastic Optimization:
https://arxiv.org/abs/1412.6980
.. _Decoupled Weight Decay Regularization:
https://arxiv.org/abs/1711.05101
.. _On the Convergence of Adam and Beyond:
https://openreview.net/forum?id=ryQu7f-RZ
"""

def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
if not 0.0 <= lr:
raise ValueError("Invalid learning rate: {}".format(lr))
if not 0.0 <= eps:
raise ValueError("Invalid epsilon value: {}".format(eps))
if not 0.0 <= betas < 1.0:
raise ValueError("Invalid beta parameter at index 0: {}".format(betas))
if not 0.0 <= betas < 1.0:
raise ValueError("Invalid beta parameter at index 1: {}".format(betas))
defaults = dict(lr=lr, betas=betas, eps=eps,

def __setstate__(self, state):
for group in self.param_groups:

[docs]    def step(self, closure=None):
"""Performs a single optimization step.

Arguments:
closure (callable, optional): A closure that reevaluates the model
and returns the loss.
"""
loss = None
if closure is not None:
loss = closure()

for group in self.param_groups:
for p in group['params']:
continue

# Perform stepweight decay
p.data.mul_(1 - group['lr'] * group['weight_decay'])

# Perform optimization step

state = self.state[p]

# State initialization
if len(state) == 0:
state['step'] = 0
# Exponential moving average of gradient values
state['exp_avg'] = torch.zeros_like(p.data, memory_format=torch.preserve_format)
# Exponential moving average of squared gradient values
state['exp_avg_sq'] = torch.zeros_like(p.data, memory_format=torch.preserve_format)
# Maintains max of all exp. moving avg. of sq. grad. values
state['max_exp_avg_sq'] = torch.zeros_like(p.data, memory_format=torch.preserve_format)

exp_avg, exp_avg_sq = state['exp_avg'], state['exp_avg_sq']
max_exp_avg_sq = state['max_exp_avg_sq']
beta1, beta2 = group['betas']

state['step'] += 1
bias_correction1 = 1 - beta1 ** state['step']
bias_correction2 = 1 - beta2 ** state['step']

# Decay the first and second moment running average coefficient
# Maintains the maximum of all 2nd moment running avg. till now
torch.max(max_exp_avg_sq, exp_avg_sq, out=max_exp_avg_sq)
# Use the max. for normalizing running avg. of gradient
else:

step_size = group['lr'] / bias_correction1

return loss ## Docs

Access comprehensive developer documentation for PyTorch

View Docs

## Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials