dlpy.lr_scheduler.ReduceLROnPlateau

class dlpy.lr_scheduler.ReduceLROnPlateau(conn, learning_rate, gamma=0.1, cool_down_iters=10, patience=10)

Bases: dlpy.lr_scheduler.FCMPLR

Reduce learning rate on plateau learning rate scheduler Reduce learning rate when loss has stopped improving for a certain number of epochs(patience). Example:

lr_scheduler = ReduceLROnPlateau(conn=sess, cool_down_iters=2, gamma=0.1, learning_rate=0.01, patience=3) solver = MomentumSolver(lr_scheduler = lr_scheduler, clip_grad_max = 100, clip_grad_min = -100)
Parameters:
conn : CAS

Specifies the CAS connection object.

learning_rate : double, optional

Specifies the initial learning rate.

gamma : double, optional

Specifies the gamma for the learning rate policy.

cool_down_iters : int, optional

Specifies number of iterations to wait before resuming normal operation after lr has been reduced.

patience : int, optional

Specifies number of epochs with no improvement after which learning rate will be reduced.

Returns:
ReduceLROnPlateau
__init__(conn, learning_rate, gamma=0.1, cool_down_iters=10, patience=10)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(conn, learning_rate[, gamma, …]) Initialize self.
clear()
get(k[,d])
items()
keys()
pop(k[,d]) If key is not found, d is returned if given, otherwise KeyError is raised.
popitem() as a 2-tuple; but raise KeyError if D is empty.
setdefault(k[,d])
update([E, ]**F) If E present and has a .keys() method, does: for k in E: D[k] = E[k] If E present and lacks .keys() method, does: for (k, v) in E: D[k] = v In either case, this is followed by: for k, v in F.items(): D[k] = v
values()