Skip to content

Instantly share code, notes, and snippets.

Last active May 31, 2019
What would you like to do?
from torch.optim.optimizer import Optimizer, required
class LARS(Optimizer):
def __init__(self, params, lr=required, momentum=0, dampening=0,
weight_decay=0, nesterov=False, eta=0.001):
if lr is not required and lr < 0.0:
raise ValueError("Invalid learning rate: {}".format(lr))
if momentum < 0.0:
raise ValueError("Invalid momentum value: {}".format(momentum))
if weight_decay < 0.0:
raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
defaults = dict(lr=lr, momentum=momentum, dampening=dampening,
weight_decay=weight_decay, nesterov=nesterov, eta=eta)
if nesterov and (momentum <= 0 or dampening != 0):
raise ValueError("Nesterov momentum requires a momentum and zero dampening")
super().__init__(params, defaults)
def __setstate__(self, state):
for group in self.param_groups:
group.setdefault('nesterov', False)
def step(self, closure=None):
"""Performs a single optimization step.
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:
weight_decay = group['weight_decay']
momentum = group['momentum']
dampening = group['dampening']
nesterov = group['nesterov']
eta = group['eta']
for p in group['params']:
if p.grad is None:
d_p =
d_pn = d_p.norm()#new
if weight_decay != 0:
if momentum != 0:
param_state = self.state[p]
if 'momentum_buffer' not in param_state:
buf = param_state['momentum_buffer'] = torch.zeros_like(
buf = param_state['momentum_buffer']
buf.mul_(momentum).add_(1 - dampening, d_p)
if nesterov:
d_p = d_p.add(momentum, buf)
d_p = buf
rho = eta * / (1e-15 + d_pn)#new['lr'] * rho, d_p)#changed
return loss
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment