optimizer.sgd.SGD Class Reference

Collaboration diagram for optimizer.sgd.SGD:

Public Member Functions
	__init__ (self, learning_rate=0.001, momentum=0.0)

Data Fields
	momentum
	velocity
Data Fields inherited from optimizer.optimizer.Optimizer
	learning_rate
	nums_trainable_ops

Detailed Description

Stochastic Gradient Descent (SGD) optimizer.

Definition at line 4 of file sgd.py.

Constructor & Destructor Documentation

__init__()

optimizer.sgd.SGD.__init__	(		self,
			learning_rate = 0.001,
			momentum = 0.0
	)

Initialize the SGD optimizer.
Args:
    learning_rate (float): The learning rate for optimization.
    momentum (float): Momentum factor (default: 0.0).

Reimplemented from optimizer.optimizer.Optimizer.

Definition at line 8 of file sgd.py.

    def __init__(self, learning_rate=0.001, momentum=0.0):
        """
        Initialize the SGD optimizer.
        Args:
            learning_rate (float): The learning rate for optimization.
            momentum (float): Momentum factor (default: 0.0).
        """
        super().__init__(learning_rate)
 
        if momentum != 0.0:
            raise NotImplementedError(
                "Momentum is not supported in the current version of SGD.")
        self.momentum = momentum
        self.velocity = None

References optimizer.sgd.SGD.__init__().

Referenced by optimizer.sgd.SGD.__init__().

Field Documentation

momentum

optimizer.sgd.SGD.momentum

Definition at line 20 of file sgd.py.

velocity

optimizer.sgd.SGD.velocity

Definition at line 21 of file sgd.py.

---

The documentation for this class was generated from the following file:

• runtime/onert/api/python/package/experimental/train/optimizer/sgd.py