torch.optim.adam.Adam Class Reference

Inheritance diagram for torch.optim.adam.Adam:

Public Member Functions
def	__init__ (self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0, amsgrad=False)
def	__setstate__ (self, state)
def	step (self, closure=None)

Detailed Description

Definition at line 6 of file adam.py.

Member Function Documentation

def torch.optim.adam.Adam.step	(		self,
			closure = None
	)

Performs a single optimization step.

Arguments:
    closure (callable, optional): A closure that reevaluates the model
and returns the loss.

Definition at line 49 of file adam.py.

---

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

• torch/optim/adam.py