def __init__(self,
params,
initial_accum=0.1,
learning_rate=0.001,
lr_power=-0.5,
l1=0.0,
l2=0.0,
use_locking=False,
loss_scale=1.0,
weight_decay=0.0):
super(FTRL, self).__init__(learning_rate, params)
_check_param(initial_accum, learning_rate, lr_power, l1, l2,
use_locking, loss_scale, weight_decay, self.cls_name)
self.moments = self.parameters.clone(prefix="moments",
init=initial_accum)
self.linear = self.parameters.clone(prefix="linear", init='zeros')
self.l1 = l1
self.l2 = l2
self.lr_power = lr_power
self.reciprocal_scale = 1.0 / loss_scale
self.weight_decay = weight_decay
self.decay_tf = tuple((lambda: True)() for x in self.parameters)
self.hyper_map = C.HyperMap()
self.opt = P.ApplyFtrl(use_locking=use_locking)
self.one = Tensor(1, mstype.int32)
def __init__(self,
params,
initial_accum=0.1,
learning_rate=0.001,
lr_power=-0.5,
l1=0.0,
l2=0.0,
use_locking=False,
loss_scale=1.0,
weight_decay=0.0):
super(FTRL, self).__init__(learning_rate,
params,
loss_scale=loss_scale)
if self.is_group:
raise RuntimeError(
f"The {self.cls_name} optimizer cannot support group setting.")
_check_param(initial_accum, lr_power, l1, l2, use_locking,
weight_decay, self.cls_name)
self.moments = self.parameters.clone(prefix="moments",
init=initial_accum)
self.linear = self.parameters.clone(prefix="linear", init='zeros')
self.l1 = l1
self.l2 = l2
self.lr_power = lr_power
self.weight_decay = weight_decay
self.decay_tf = tuple((lambda: True)() for x in self.parameters)
self.hyper_map = C.HyperMap()
self.opt = P.ApplyFtrl(use_locking=use_locking)
self.sparse_opt = P.SparseApplyFtrl(learning_rate,
l1,
l2,
lr_power,
use_locking=use_locking)
def __init__(self, params, initial_accum=0.1, learning_rate=0.001, lr_power=-0.5, l1=0.0, l2=0.0,
use_locking=False, loss_scale=1.0, weight_decay=0.0):
super(FTRL, self).__init__(learning_rate, params, weight_decay, loss_scale=loss_scale)
if self.dynamic_lr or self.is_group_lr:
raise ValueError('Dynamic learning rate or group learning rate is currently not supported.')
_check_param(initial_accum, lr_power, l1, l2, use_locking, self.cls_name)
self.moments = self.parameters.clone(prefix="moments", init=initial_accum)
self.linear = self.parameters.clone(prefix="linear", init='zeros')
self.l1 = l1
self.l2 = l2
self.lr = learning_rate
self.lr_power = lr_power
if not self.is_group:
self.decay_flags = tuple((lambda: True)() for x in self.parameters)
self.hyper_map = C.HyperMap()
self.opt = P.ApplyFtrl(use_locking=use_locking)
self.use_locking = use_locking
self.sparse_opt = P.SparseApplyFtrl(learning_rate, l1, l2, lr_power, use_locking=use_locking)
self._ps_pull = P.Pull()
self._ps_push = P.Push("Ftrl", [0, 1, 2])
self._ps_push.add_prim_attr("init_accum", initial_accum)
self._ps_push.add_prim_attr("lr", learning_rate)
self._ps_push.add_prim_attr("l1", l1)
self._ps_push.add_prim_attr("l2", l2)
self._ps_push.add_prim_attr("lr_power", lr_power)
def __init__(self):
super(ApplyFtrlNet, self).__init__()
self.apply_ftrl = P.ApplyFtrl()
self.lr = 0.001
self.l1 = 0.0
self.l2 = 0.0
self.lr_power = -0.5
self.var = Parameter(Tensor(np.random.rand(3, 3).astype(np.float32)), name="var")
self.accum = Parameter(Tensor(np.random.rand(3, 3).astype(np.float32)), name="accum")
self.linear = Parameter(Tensor(np.random.rand(3, 3).astype(np.float32)), name="linear")
'block': P.ReduceProd(),
'desc_const': [0],
'desc_inputs': [[3, 2]],
'desc_bprop': [[2]]}),
('ReduceProd_1', {
'block': P.ReduceProd(keep_dims=True),
'desc_const': [0],
'desc_inputs': [[3, 2]],
'desc_bprop': [[1, 2]]}),
('CumProd', {
'block': P.CumProd(),
'desc_const': [0],
'desc_inputs': [[3, 2]],
'desc_bprop': [[3, 2]]}),
('ApplyFtrl', {
'block': P.ApplyFtrl(),
'desc_const': [0.001, 0.0, 0.0, -0.5],
'desc_inputs': [[3, 3], [3, 3], [3, 3], [3, 3]],
'desc_bprop': [3, 3],
'skip': ['backward']}),
('ApplyRMSProp', {
'block': P.ApplyRMSProp(),
'desc_const': [0.9, 0.0, 1e-10, 0.001],
'desc_inputs': [[3, 3], [3, 3], [3, 3], [3, 3]],
'desc_bprop': [3, 3],
'skip': ['backward']}),
('ApplyCenteredRMSProp', {
'block': P.ApplyCenteredRMSProp(),
'desc_const': [0.9, 0.0, 1e-10, 0.001],
'desc_inputs': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3]],
'desc_bprop': [3, 3],
def __init__(self, var, accum, linear):
super(ApplyFtrlNet, self).__init__()
self.apply_ftrl = P.ApplyFtrl()
self.var = Parameter(var, name="var")
self.accum = Parameter(accum, name="accum")
self.linear = Parameter(linear, name="linear")
