def __init__(self,
params,
learning_rate=1e-3,
beta1=0.9,
beta2=0.999,
eps=1e-8,
use_locking=False,
use_nesterov=False,
weight_decay=0.0,
loss_scale=1.0):
super(Adam, self).__init__(learning_rate, params, weight_decay,
loss_scale)
_check_param_value(beta1, beta2, eps, weight_decay, self.cls_name)
validator.check_value_type("use_locking", use_locking, [bool],
self.cls_name)
validator.check_value_type("use_nesterov", use_nesterov, [bool],
self.cls_name)
self.beta1 = Tensor(beta1, mstype.float32)
self.beta2 = Tensor(beta2, mstype.float32)
self.beta1_power = Parameter(initializer(1, [1], mstype.float32),
name="beta1_power")
self.beta2_power = Parameter(initializer(1, [1], mstype.float32),
name="beta2_power")
self.eps = eps
self.moment1 = self.parameters.clone(prefix="moment1", init='zeros')
self.moment2 = self.parameters.clone(prefix="moment2", init='zeros')
self.hyper_map = C.HyperMap()
self.opt = P.Adam(use_locking, use_nesterov)
self.sparse_opt = P.SparseApplyAdam(use_locking, use_nesterov)
def __init__(self):
super(Net, self).__init__()
self.sparse_apply_adam = P.SparseApplyAdam()
self.var = Parameter(Tensor(np.ones([3, 3, 3]).astype(np.float32)),
name="var")
self.m = Parameter(Tensor(np.ones([3, 3, 3]).astype(np.float32)),
name="m")
self.v = Parameter(Tensor(np.ones([3, 3, 3]).astype(np.float32)),
name="v")