LambdaDecay

class paddle.fluid.dygraph.learning_rate_scheduler. LambdaDecay ( learning_rate, lr_lambda ) [source]
Api_attr

imperative

Sets the learning rate of optimizer to the initial lr times a multiplicative factor, and this multiplicative factor is computed by function lr_lambda . lr_lambda is function which receives epoch .

The algorithm can be described as the code below.

learning_rate = 0.5        # init learning_rate
lr_lambda = lambda epoch: 0.95 ** epoch

learning_rate = 0.5        # epoch 0
learning_rate = 0.475      # epoch 1
learning_rate = 0.45125    # epoch 2
Parameters

  • learning_rate (float|int) – The initial learning rate. It can be set to python float or int number.

  • lr_lambda (function) – A function which computes a multiplicative factor given an integer parameter epoch , and then multiply the initial learning rate by this multiplicative factor.

Returns

None.

Examples

import paddle.fluid as fluid
import numpy as np
import paddle
with fluid.dygraph.guard():
    x = np.random.uniform(-1, 1, [10, 10]).astype("float32")
    linear = paddle.nn.Linear(10, 10)
    input = fluid.dygraph.to_variable(x)
    scheduler = fluid.dygraph.LambdaDecay(0.5, lr_lambda=lambda x: 0.95**x)
    adam = fluid.optimizer.Adam(learning_rate = scheduler, parameter_list = linear.parameters())

    for epoch in range(6):
        for batch_id in range(5):
            out = linear(input)
            loss = paddle.mean(out)
            adam.minimize(loss)
        scheduler.epoch()

        print("epoch:%d, current lr is %f" .format(epoch, adam.current_step_lr()))
        # epoch:0, current lr is 0.5
        # epoch:1, current lr is 0.475
        # epoch:2, current lr is 0.45125
create_lr_var ( lr )

create_lr_var

convert lr from float to variable

Parameters

lr – learning rate

Returns

learning rate variable

epoch ( epoch=None )

epoch

compueted learning_rate and update it when invoked.

set_dict ( state_dict )

set_dict

Loads the schedulers state.

set_state_dict ( state_dict )

set_state_dict

Loads the schedulers state.

state_dict ( )

state_dict

Returns the state of the scheduler as a dict.

It is a subset of self.__dict__ .