本文整理汇总了Python中pytorch_pretrained_bert.optimization.warmup_linear方法的典型用法代码示例。如果您正苦于以下问题：Python optimization.warmup_linear方法的具体用法？Python optimization.warmup_linear怎么用？Python optimization.warmup_linear使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pytorch_pretrained_bert.optimization的用法示例。
在下文中一共展示了optimization.warmup_linear方法的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: from pytorch_pretrained_bert import optimization [as 别名]
# 或者: from pytorch_pretrained_bert.optimization import warmup_linear [as 别名]
def __init__(self, params, lr, warmup=-1, t_total=-1, schedule='warmup_linear',
betas=(0.9, 0.999), eps=1e-6, weight_decay_rate=0.01,
max_grad_norm=1.0):
if not lr >= 0.0:
raise ValueError("Invalid learning rate: {} - should be >= 0.0".format(lr))
if not 0.0 <= warmup < 1.0 and not warmup == -1:
raise ValueError("Invalid warmup: {} - should be in [0.0, 1.0[ or -1".format(warmup))
if not 0.0 <= eps:
raise ValueError("Invalid epsilon value: {}".format(eps))
if not 0.0 <= betas[0] < 1.0:
raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
if not 0.0 <= betas[1] < 1.0:
raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
defaults = dict(lr=lr, schedule=schedule, warmup=warmup, t_total=t_total,
betas=betas, eps=eps, weight_decay_rate=weight_decay_rate,
max_grad_norm=max_grad_norm)
super(Adamax, self).__init__(params, defaults) 示例2: __init__
# 需要导入模块: from pytorch_pretrained_bert import optimization [as 别名]
# 或者: from pytorch_pretrained_bert.optimization import warmup_linear [as 别名]
def __init__(self, params, lr, warmup=-1, t_total=-1, schedule='warmup_linear',
betas=(0.9, 0.999), eps=1e-6, weight_decay=0.01,
max_grad_norm=1.0):
if not lr >= 0.0:
raise ValueError("Invalid learning rate: {} - should be >= 0.0".format(lr))
if not 0.0 <= warmup < 1.0 and not warmup == -1:
raise ValueError("Invalid warmup: {} - should be in [0.0, 1.0[ or -1".format(warmup))
if not 0.0 <= eps:
raise ValueError("Invalid epsilon value: {}".format(eps))
if not 0.0 <= betas[0] < 1.0:
raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
if not 0.0 <= betas[1] < 1.0:
raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
defaults = dict(lr=lr, schedule=schedule, warmup=warmup, t_total=t_total,
betas=betas, eps=eps, weight_decay=weight_decay,
max_grad_norm=max_grad_norm)
super(Adamax, self).__init__(params, defaults) 示例3: schedule_func
# 需要导入模块: from pytorch_pretrained_bert import optimization [as 别名]
# 或者: from pytorch_pretrained_bert.optimization import warmup_linear [as 别名]
def schedule_func(sch):
try:
f = eval(sch)
except:
f = warmup_linear
return f 示例4: warmup_linear
# 需要导入模块: from pytorch_pretrained_bert import optimization [as 别名]
# 或者: from pytorch_pretrained_bert.optimization import warmup_linear [as 别名]
def warmup_linear(x, warmup=0.002):
if x < warmup:
return x/warmup
return 1.0 - x 示例5: __init__
# 需要导入模块: from pytorch_pretrained_bert import optimization [as 别名]
# 或者: from pytorch_pretrained_bert.optimization import warmup_linear [as 别名]
def __init__(
self,
params,
lr,
warmup=-1,
t_total=-1,
schedule="warmup_linear",
betas=(0.9, 0.999),
eps=1e-6,
weight_decay=0.01,
max_grad_norm=1.0,
):
if not lr >= 0.0:
raise ValueError("Invalid learning rate: {} - should be >= 0.0".format(lr))
if not 0.0 <= warmup < 1.0 and not warmup == -1:
raise ValueError("Invalid warmup: {} - should be in [0.0, 1.0[ or -1".format(warmup))
if not 0.0 <= eps:
raise ValueError("Invalid epsilon value: {}".format(eps))
if not 0.0 <= betas[0] < 1.0:
raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
if not 0.0 <= betas[1] < 1.0:
raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
defaults = dict(
lr=lr,
schedule=schedule,
warmup=warmup,
t_total=t_total,
betas=betas,
eps=eps,
weight_decay=weight_decay,
max_grad_norm=max_grad_norm,
)
super(Adamax, self).__init__(params, defaults)