ModelAverage

class paddle.fluid.optimizer. ModelAverage ( average_window_rate, min_average_window=10000, max_average_window=10000, regularization=None, name=None ) [source]
api_attr

Static Graph

The ModelAverage optimizer accumulates specific continuous historical parameters during training. The accumulated historical range can be controlled by the passed average_window_rate argument. The averaged Parameter are used in the prediction, which usually can improve the accuracy of the prediction.

Accumulate the average of the Parameter in the sliding window, the result will be saved in a temporary variable, can be applied to the current model’s Parameter by calling the apply() method, and the current model Parameter can be restored by calling the restore() method.

The window size for calculating the average is determined by average_window_rate, min_average_window, max_average_window and the current Parameter update times (num_updates).

When the cumulative times (num_accumulates) is greater than the specific window threshold (average_window), the accumulated Parameter temporary variable is set to 0.0. The following example will help to understand the role of these arguments:

if num_accumulates >= min_average_window and num_accumulates >= min(max_average_window, num_updates * average_window_rate):
    num_accumulates = 0

In the above conditional judgment statement, num_accumulates indicates the current accumulated number, which can be abstractly understood as the length of the cumulative window. The length of the window must be at least the length set by the min_average_window argument, and cannot exceed the length specified by the max_average_window argument or num_updates * average_window_rate, where num_updates indicates the current Parameter update times, average_window_rate is a coefficient that calculates the length of the window.

Parameters

  • average_window_rate (float) – The calculate ratio of the window length relative to Parameter update times.

  • min_average_window (int, optional) – the minimum size of average window length. The default value is 10000.

  • max_average_window (int, optional) – The maximum size of average window length. The default value is 10000.

  • regularization (WeightDecayRegularizer, optional) –

    The strategy of regularization. There are two method:

    api_fluid_regularizer_L1Decay , api_fluid_regularizer_L2Decay . If a parameter has set

    System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/fluid/optimizer.py:docstring of paddle.fluid.optimizer.ModelAverage, line 41)

    Definition list ends without a blank line; unexpected unindent.

    regularizer using api_fluid_ParamAttr already, the regularization setting here in optimizer will be ignored for this parameter. Otherwise, the regularization setting here in optimizer will take effect. Default None, meaning there is no regularization.

  • name (str, optional) – Normally there is no need for user to set this property. For more information, please refer to Name. The default value is None.

Examples

import paddle.fluid as fluid
import numpy

# First create the Executor.
place = fluid.CPUPlace()  # fluid.CUDAPlace(0)
exe = fluid.Executor(place)

train_program = fluid.Program()
startup_program = fluid.Program()
with fluid.program_guard(train_program, startup_program):
    # build net
    data = fluid.data(name='X', shape=[None, 1], dtype='float32')
    hidden = fluid.layers.fc(input=data, size=10)
    loss = fluid.layers.mean(hidden)
    optimizer = fluid.optimizer.Momentum(learning_rate=0.2, momentum=0.1)
    optimizer.minimize(loss)

    # build ModelAverage optimizer
    model_average = fluid.optimizer.ModelAverage(0.15,
                                                 min_average_window=10000,
                                                 max_average_window=12500)

    exe.run(startup_program)
    for i in range(12500):
        x = numpy.random.random(size=(10, 1)).astype('float32')
        outs = exe.run(program=train_program,
                       feed={'X': x},
                       fetch_list=[loss.name])

    # apply ModelAverage
    with model_average.apply(exe):
        x = numpy.random.random(size=(10, 1)).astype('float32')
        exe.run(program=train_program,
                feed={'X': x},
                fetch_list=[loss.name])
apply ( executor, need_restore=True )

apply

Apply the average of the cumulative Parameter to the parameters of the current model.

Parameters

  • executor (fluid.Executor) – The current network executor.

  • need_restore (bool) – Restore flag variable, if set to True, the network will restore the parameters of the network to the default value, if set to False, it will not be restored. The default value is True.

Examples

import paddle.fluid as fluid
import numpy

# First create the Executor.
place = fluid.CPUPlace()  # fluid.CUDAPlace(0)
exe = fluid.Executor(place)

train_program = fluid.Program()
startup_program = fluid.Program()
with fluid.program_guard(train_program, startup_program):
    # build net
    data = fluid.data(name='X', shape=[None, 1], dtype='float32')
    hidden = fluid.layers.fc(input=data, size=10)
    loss = fluid.layers.mean(hidden)
    optimizer = fluid.optimizer.Momentum(learning_rate=0.2, momentum=0.1)
    optimizer.minimize(loss)

    # build ModelAverage optimizer
    model_average = fluid.optimizer.ModelAverage(0.15,
                                                min_average_window=10000,
                                                max_average_window=12500)

    exe.run(startup_program)
    for i in range(12500):
        x = numpy.random.random(size=(10, 1)).astype('float32')
        outs = exe.run(program=train_program,
                    feed={'X': x},
                    fetch_list=[loss.name])

    # apply ModelAverage
    with model_average.apply(exe):
        x = numpy.random.random(size=(10, 1)).astype('float32')
        exe.run(program=train_program,
                feed={'X': x},
                fetch_list=[loss.name])
restore ( executor )

restore

Restore Parameter values of current model.

Parameters

executor (fluid.Executor) – The current network executor.

Examples

import paddle.fluid as fluid
import numpy

# First create the Executor.
place = fluid.CPUPlace()  # fluid.CUDAPlace(0)
exe = fluid.Executor(place)

train_program = fluid.Program()
startup_program = fluid.Program()
with fluid.program_guard(train_program, startup_program):
    # build net
    data = fluid.data(name='X', shape=[None, 1], dtype='float32')
    hidden = fluid.layers.fc(input=data, size=10)
    loss = fluid.layers.mean(hidden)
    optimizer = fluid.optimizer.Momentum(learning_rate=0.2, momentum=0.1)
    optimizer.minimize(loss)

    # build ModelAverage optimizer
    model_average = fluid.optimizer.ModelAverage(0.15,
                                                min_average_window=10000,
                                                max_average_window=12500)

    exe.run(startup_program)
    for i in range(12500):
        x = numpy.random.random(size=(10, 1)).astype('float32')
        outs = exe.run(program=train_program,
                    feed={'X': x},
                    fetch_list=[loss.name])

    # apply ModelAverage
    with model_average.apply(exe, False):
        x = numpy.random.random(size=(10, 1)).astype('float32')
        exe.run(program=train_program,
                feed={'X': x},
                fetch_list=[loss.name])

    # restore Parameters
    model_average.restore(exe)
append_regularization_ops ( parameters_and_grads, regularization=None )

append_regularization_ops

Create and add backward regularization Operators

Creates and adds backward regularization operators in the BlockDesc. This will add gradients of the regularizer function to the gradients of the parameters and return these modified gradients. This is the same as implementing weight decay in optimizers for regularization.

Parameters

  • parameters_and_grads – A list of (parameters, gradients) pairs that need to be regularized.

  • regularization – A global regularizer. If the parameter is not set. It will be applied with regularizer.

Returns

list of (parameters, gradients) pair with the regularized gradient

Return type

list[(Variable, Variable)]

Raises

Exception – Unknown regularization type

apply_gradients ( params_grads )

apply_gradients

Second part of minimize, appending optimization operators for given params_grads pairs.

Parameters

params_grads (list) – list of (param, grad) pair to do optimization.

Returns

A list of operators appended to the current program.

Return type

list

Examples

import paddle.fluid as fluid
loss = network()
optimizer = fluid.optimizer.SGD(learning_rate=0.1)
params_grads = optimizer.backward(loss)
# you may append operations for params_grads here
# ...
optimizer.apply_gradients(params_grads)
apply_optimize ( loss, startup_program, params_grads )

apply_optimize

Second part of minimize, appending optimization operators for given params_grads pairs. :param loss: loss variable to run optimizations. :type loss: Variable :param startup_program: startup_program for initializing parameters

System Message: ERROR/3 (/usr/local/lib/python3.8/site-packages/paddle/fluid/optimizer.py:docstring of paddle.fluid.optimizer.Optimizer.apply_optimize, line 6)

Unexpected indentation.

in parameter_list.

System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/fluid/optimizer.py:docstring of paddle.fluid.optimizer.Optimizer.apply_optimize, line 7)

Block quote ends without a blank line; unexpected unindent.

Parameters

params_grads (list) – list of (param, grad) pair to do optimization.

Returns

A list of operators appended to the current program.

Return type

list

backward ( loss, startup_program=None, parameter_list=None, no_grad_set=None, callbacks=None )

backward

The first part of minimize, do auto-diff to append backward operations for the current program.

Parameters

  • loss (Variable) – loss variable to run optimizations.

  • startup_program (Program, optional) – api_fluid_Program for initializing parameters in parameter_list. The default value is None, at this time api_fluid_default_startup_program will be used.

  • parameter_list (Iterable, optional) – Iterable of Variable or Variable.name to update to minimize loss. The default value is None, at this time all parameters will be updated.

  • no_grad_set (set, optional) – Set of Variable or Variable.name that don’t need to be updated. The default value is None.

  • callbacks (list, optional) – list of callable objects to run when appending backward operator for one parameter. The default value is None.

Returns

list of (param, grad) variable pairs, param is Parameter,

grad is the gradient value corresponding to the parameter.

Return type

list

Examples

See examples in apply_gradients.

clear_gradients ( )

clear_gradients

Clear the gradients of all optimized parameters for model.

If not, new gradient will accumulat on previous gradient.

Returns

None

Examples

import paddle.fluid as fluid
import numpy as np

with fluid.dygraph.guard():
    value = np.arange(26).reshape(2, 13).astype("float32")
    a = fluid.dygraph.to_variable(value)
    linear = fluid.Linear(13, 5, dtype="float32")
    # This can be any optimizer supported by dygraph.
    adam = fluid.optimizer.Adam(learning_rate = 0.01,
                                parameter_list = linear.parameters())
    out = linear(a)
    out.backward()
    adam.minimize(out)
    adam.clear_gradients()
current_step_lr ( )

current_step_lr

Api_attr

imperative

Get current step learning rate. The return value is all the same When LearningRateDecay is not used, otherwise return the step learning rate.

Returns

The learning rate of the current step.

Return type

float

Examples

import paddle.fluid as fluid
import numpy as np

# example1: LearningRateDecay is not used, return value is all the same
with fluid.dygraph.guard():
    emb = fluid.dygraph.Embedding([10, 10])
    adam = fluid.optimizer.Adam(0.001, parameter_list = emb.parameters())
    lr = adam.current_step_lr()
    print(lr) # 0.001

# example2: PiecewiseDecay is used, return the step learning rate
with fluid.dygraph.guard():
    inp = np.random.uniform(-0.1, 0.1, [10, 10]).astype("float32")
    linear = fluid.dygraph.nn.Linear(10, 10)
    inp = fluid.dygraph.to_variable(inp)
    out = linear(inp)
    loss = fluid.layers.reduce_mean(out)

    bd = [2, 4, 6, 8]
    value = [0.2, 0.4, 0.6, 0.8, 1.0]
    adam = fluid.optimizer.Adam(fluid.dygraph.PiecewiseDecay(bd, value, 0),
                           parameter_list=linear.parameters())

    # first step: learning rate is 0.2
    np.allclose(adam.current_step_lr(), 0.2, rtol=1e-06, atol=0.0) # True

    # learning rate for different steps
    ret = [0.2, 0.2, 0.4, 0.4, 0.6, 0.6, 0.8, 0.8, 1.0, 1.0, 1.0, 1.0]
    for i in range(12):
        adam.minimize(loss)
        lr = adam.current_step_lr()
        np.allclose(lr, ret[i], rtol=1e-06, atol=0.0) # True
minimize ( loss, startup_program=None, parameter_list=None, no_grad_set=None )

minimize

Add operations to minimize loss by updating parameter_list.

Parameters

  • loss (Variable) – A Variable containing the value to minimize.

  • startup_program (Program, optional) – api_fluid_Program for initializing parameters in parameter_list. The default value is None, at this time api_fluid_default_startup_program will be used.

  • parameter_list (Iterable, optional) – Iterable of Variable or Variable.name to update to minimize loss. The default value is None, at this time all parameters will be updated.

  • no_grad_set (set, optional) – Set of Variable or Variable.name that don’t need to be updated. The default value is None.

Returns

tuple (optimize_ops, params_grads), A list of operators appended by minimize and a list of (param, grad) variable pairs, param is Parameter, grad is the gradient value corresponding to the parameter. The returned tuple can be passed to fetch_list in Executor.run() to indicate program pruning. If so, the program will be pruned by feed and fetch_list before run, see details in Executor.

Return type

tuple

Examples

Please refer to the example of current Optimizer.

set_dict ( state_dict )

set_dict

Load optimizer state dict. For Adam optimizer, contains beta1, beta2, momentum etc. If LearningRateDecay have been used, global_step will be changed.

Parameters

state_dict (dict) – Dict contains all the Variable needed by optimizer

Returns

None

Examples

import paddle
import paddle.fluid as fluid

paddle.disable_static()

emb = paddle.nn.Embedding(10, 10)

state_dict = emb.state_dict()
fluid.save_dygraph(state_dict, "paddle_dy")

scheduler = paddle.optimizer.lr.NoamDecay(
    d_model=0.01, warmup_steps=100, verbose=True)
adam = paddle.optimizer.Adam(
    learning_rate=scheduler,
    parameters=emb.parameters())
state_dict = adam.state_dict()
fluid.save_dygraph(state_dict, "paddle_dy")

para_state_dict, opti_state_dict = fluid.load_dygraph("paddle_dy")
set_lr ( value )

set_lr

Api_attr

imperative

Set the value of the learning rate manually in the optimizer. If the optimizer use LearningRateDecay, this API cannot be invoked, because it will lead to conflict.

Parameters

value (float|Variable) – the value of learning rate

Returns

None

Examples

import paddle.fluid as fluid

with fluid.dygraph.guard():
    linear = fluid.dygraph.nn.Linear(10, 10)

    adam = fluid.optimizer.Adam(0.1, parameter_list=linear.parameters())

    # set learning rate manually by python float value
    lr_list = [0.2, 0.3, 0.4, 0.5, 0.6]
    for i in range(5):
        adam.set_lr(lr_list[i])
        lr = adam.current_step_lr()
        print("current lr is {}".format(lr))
    # Print:
    #    current lr is 0.2
    #    current lr is 0.3
    #    current lr is 0.4
    #    current lr is 0.5
    #    current lr is 0.6


    # set learning rate manually by framework Variable
    lr_var = fluid.layers.create_global_var(
        shape=[1], value=0.7, dtype='float32')
    adam.set_lr(lr_var)
    lr = adam.current_step_lr()
    print("current lr is {}".format(lr))
    # Print:
    #    current lr is 0.7
set_state_dict ( state_dict )

set_state_dict

Load optimizer state dict. For Adam optimizer, contains beta1, beta2, momentum etc. If LearningRateDecay have been used, global_step will be changed.

Parameters

state_dict (dict) – Dict contains all the Variable needed by optimizer

Returns

None

Examples

import paddle
import paddle.fluid as fluid

paddle.disable_static()

emb = paddle.nn.Embedding(10, 10)

state_dict = emb.state_dict()
fluid.save_dygraph(state_dict, "paddle_dy")

scheduler = paddle.optimizer.lr.NoamDecay(
    d_model=0.01, warmup_steps=100, verbose=True)
adam = paddle.optimizer.Adam(
    learning_rate=scheduler,
    parameters=emb.parameters())
state_dict = adam.state_dict()
fluid.save_dygraph(state_dict, "paddle_dy")

para_state_dict, opti_state_dict = fluid.load_dygraph("paddle_dy")
state_dict ( )

state_dict

Get state dict information from optimizer. It contain all the variable used by optimizer. For Adam optimizer, contains beta1, beta2, momentum etc. If LearningRateDecay have been used, global_step will be include in state dict. If the optimizer never be called(minimize function), the state_dict is empty.

Args: None :returns: dict contains all the variable used by optimizer :rtype: state_dict(dict)

Examples

import paddle.fluid as fluid

with fluid.dygraph.guard():
    emb = fluid.dygraph.Embedding([10, 10])

    adam = fluid.optimizer.Adam(0.001, parameter_list=emb.parameters())
    state_dict = adam.state_dict()