Source code for lmflow.optim.adam

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import torch
from torch.optim.optimizer import Optimizer



class Adam(Optimizer):
    def __init__(self, params, lr=0.001, betas=(0.9, 0.999), eps=1e-8):
        defaults = dict(lr=lr, betas=betas, eps=eps)
        super(Adam, self).__init__(params, defaults)



    def step(self, closure=None):
        loss = None
        if closure is not None:
            loss = closure()

        for group in self.param_groups:
            for p in group['params']:
                if p.grad is None:
                    continue
                grad = p.grad.data
                
                state = self.state[p]

                if len(state) == 0:
                    state['step'] = 0
                    state['exp_avg'] = torch.zeros_like(p.data)
                    state['exp_avg_sq'] = torch.zeros_like(p.data)

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

                state['step'] += 1

                exp_avg.mul_(beta1).add_(1 - beta1, grad)

                exp_avg_sq.mul_(beta2).addcmul_(1 - beta2, grad, grad)

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

                step_size = group['lr'] * (bias_correction2 ** 0.5) / bias_correction1
                denom = exp_avg_sq.sqrt().add_(group['eps'])
                p.data.addcdiv_(-step_size, exp_avg, denom)

        return loss