def _apply_dense(self, grad, var):
g_acc = self.get_slot(var, "gradient_accumulator")
gg_acc = self.get_slot(var, "gradient_squared_accumulator")
with ops.device(var.device):
global_step = array_ops.identity(self._global_step_on_worker)
return training_ops.apply_adagrad_da(
var,
g_acc,
gg_acc,
grad,
math_ops.cast(self._learning_rate_tensor, var.dtype.base_dtype),
math_ops.cast(self._l1_regularization_strength, var.dtype.base_dtype),
math_ops.cast(self._l2_regularization_strength, var.dtype.base_dtype),
global_step,
use_locking=self._use_locking)
def _apply_dense(self, grad, var):
g_acc = self.get_slot(var, "gradient_accumulator")
gg_acc = self.get_slot(var, "gradient_squared_accumulator")
with ops.device(var.device):
global_step = array_ops.identity(self._global_step_on_worker)
return training_ops.apply_adagrad_da(
var,
g_acc,
gg_acc,
grad,
math_ops.cast(self._learning_rate_tensor, var.dtype.base_dtype),
math_ops.cast(self._l1_regularization_strength, var.dtype.base_dtype),
math_ops.cast(self._l2_regularization_strength, var.dtype.base_dtype),
global_step,
use_locking=self._use_locking)
def _apply_dense(self, grad, var):
g_acc = self.get_slot(var, "gradient_accumulator")
gg_acc = self.get_slot(var, "gradient_squared_accumulator")
# Performance optimization so that worker creates a copy of the global step
# to avoid overloading the parameter server holding the global step.
with ops.device(grad[0].device):
global_step = array_ops.identity(self._global_step) + 1
return training_ops.apply_adagrad_da(
var,
g_acc,
gg_acc,
grad,
math_ops.cast(self._learning_rate_tensor, var.dtype.base_dtype),
math_ops.cast(self._l1_regularization_strength, var.dtype.base_dtype),
math_ops.cast(self._l2_regularization_strength, var.dtype.base_dtype),
global_step,
use_locking=self._use_locking)
def _apply_dense(self, grad, var):
g_acc = self.get_slot(var, "gradient_accumulator")
gg_acc = self.get_slot(var, "gradient_squared_accumulator")
# Performance optimization so that worker creates a copy of the global step
# to avoid overloading the parameter server holding the global step.
with ops.device(grad[0].device):
global_step = array_ops.identity(self._global_step) + 1
return training_ops.apply_adagrad_da(
var,
g_acc,
gg_acc,
grad,
math_ops.cast(self._learning_rate_tensor, var.dtype.base_dtype),
math_ops.cast(self._l1_regularization_strength, var.dtype.base_dtype),
math_ops.cast(self._l2_regularization_strength, var.dtype.base_dtype),
global_step,
use_locking=self._use_locking)