LookAhead

class paddle.incubate. LookAhead ( inner_optimizer, alpha=0.5, k=5, name=None ) [source]

This implements the Lookahead optimizer of the paper : https://arxiv.org/abs/1907.08610.

Lookahead keeps two sets of params: the fast_params and the slow_params. inner_optimizer update fast_params every training step. Lookahead updates the slow_params and fast_params every k training steps as follows:

\[ \begin{align}\begin{aligned}\begin{split}slow\_param_t &= slow\_param_{t-1} + \\alpha * (fast\_param_{t-1} - slow\_param_{t-1})\end{split}\\fast\_param_t &= slow\_param_t\end{aligned}\end{align} \]
Parameters
  • inner_optimizer (Optimizer) – The optimizer that update fast params step by step.

  • alpha (float, optional) – The learning rate of Lookahead. The default value is 0.5.

  • k (int, optional) – The slow params is updated every k steps. The default value is 5.

  • 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 numpy as np
>>> import paddle
>>> import paddle.nn as nn

>>> BATCH_SIZE = 16
>>> BATCH_NUM = 4
>>> EPOCH_NUM = 4

>>> IMAGE_SIZE = 784
>>> CLASS_NUM = 10
>>> # define a random dataset
>>> class RandomDataset(paddle.io.Dataset):
...     def __init__(self, num_samples):
...         self.num_samples = num_samples
...     def __getitem__(self, idx):
...         image = np.random.random([IMAGE_SIZE]).astype('float32')
...         label = np.random.randint(0, CLASS_NUM - 1,
...                                 (1, )).astype('int64')
...         return image, label
...     def __len__(self):
...         return self.num_samples

>>> class LinearNet(nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self._linear = nn.Linear(IMAGE_SIZE, CLASS_NUM)
...         self.bias = self._linear.bias
...     @paddle.jit.to_static
...     def forward(self, x):
...         return self._linear(x)

>>> def train(layer, loader, loss_fn, opt):
...     for epoch_id in range(EPOCH_NUM):
...         for batch_id, (image, label) in enumerate(loader()):
...             out = layer(image)
...             loss = loss_fn(out, label)
...             loss.backward()
...             opt.step()
...             opt.clear_grad()
...             print("Train Epoch {} batch {}: loss = {}".format(
...                 epoch_id, batch_id, np.mean(loss.numpy())))
>>> layer = LinearNet()
>>> loss_fn = nn.CrossEntropyLoss()
>>> optimizer = paddle.optimizer.SGD(learning_rate=0.1, parameters=layer.parameters())
>>> lookahead = paddle.incubate.LookAhead(optimizer, alpha=0.2, k=5)

>>> # create data loader
>>> dataset = RandomDataset(BATCH_NUM * BATCH_SIZE)
>>> loader = paddle.io.DataLoader(
...     dataset,
...     batch_size=BATCH_SIZE,
...     shuffle=True,
...     drop_last=True,
...     num_workers=2)

>>> 
>>> train(layer, loader, loss_fn, lookahead)
step ( )

step

Execute the optimizer and update parameters once.

Returns

None

Examples

>>> import paddle
>>> inp = paddle.rand([1,10], dtype="float32")
>>> linear = paddle.nn.Linear(10, 1)
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> sgd = paddle.optimizer.SGD(learning_rate=0.1,parameters=linear.parameters())
>>> lookahead = paddle.incubate.LookAhead(sgd, alpha=0.2, k=5)
>>> loss.backward()
>>> lookahead.step()
>>> lookahead.clear_grad()
minimize ( loss, startup_program=None, parameters=None, no_grad_set=None )

minimize

Add operations to minimize loss by updating parameters.

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

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

  • parameters (list, optional) – List of Tensor or Tensor.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 Tensor or Tensor.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) tensor pairs, param is Parameter, grad is the gradient value corresponding to the parameter. In static graph mode, 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

>>> import paddle

>>> inp = paddle.rand([1, 10], dtype="float32")
>>> linear = paddle.nn.Linear(10, 1)
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> sgd = paddle.optimizer.SGD(learning_rate=0.1,parameters=linear.parameters())
>>> lookahead = paddle.incubate.LookAhead(sgd, alpha=0.2, k=5)
>>> loss.backward()
>>> lookahead.minimize(loss)
>>> lookahead.clear_grad()
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

>>> inp = paddle.uniform([10, 10], dtype="float32", min=-0.1, max=0.1)
>>> linear = paddle.nn.Linear(10, 10)
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> optimizer = paddle.optimizer.Adam(learning_rate=0.1,
...         parameters=linear.parameters())
>>> params_grads = optimizer.backward(loss)
>>> optimizer.apply_gradients(params_grads)
backward ( loss, startup_program=None, parameters=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 (Tensor) – loss tensor to run optimizations.

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

  • parameters (list, optional) – List of Tensor or Tensor.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 Tensor or Tensor.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) tensor pairs, param is Parameter,

grad is the gradient value corresponding to the parameter.

Return type

list

Examples

>>> import paddle
>>> x = paddle.arange(26, dtype="float32").reshape([2, 13])

>>> linear = paddle.nn.Linear(13, 5)
>>> # This can be any optimizer supported by dygraph.
>>> adam = paddle.optimizer.Adam(learning_rate = 0.01,
...                             parameters = linear.parameters())
>>> out = linear(x)
>>> out.backward()
>>> adam.step()
>>> adam.clear_grad()
clear_grad ( set_to_zero=True )

clear_grad

Clear the gradients of all optimized parameters for model.

If not, new gradient will accumulat on previous gradient.

There are two method to clear grad: set_to_zero or delete grad.

Parameters

set_to_zero (bool, optional) – If set grads to zero or not, default is True.

Returns

None

Examples

>>> import paddle

>>> a = paddle.arange(26, dtype="float32").reshape([2, 13])
>>> linear = paddle.nn.Linear(13, 5)
>>> # This can be any optimizer supported by dygraph.
>>> adam = paddle.optimizer.Adam(learning_rate = 0.01,
...                             parameters = linear.parameters())
>>> out = linear(a)
>>> out.backward()
>>> adam.step()
>>> adam.clear_grad()
get_lr ( )

get_lr

Get current learning rate of optimizer. If ‘LRScheduler’ is not used, the return value is all the same. If ‘LRScheduler’ is used, the return value is the current scheduled learing rete.

Returns

The current learning rate of optimizer.

Return type

float

Examples

>>> # train on default dynamic graph mode
>>> import paddle
>>> import numpy as np
>>> emb = paddle.nn.Embedding(10, 3)

>>> ## example1: LRScheduler is not used, return the same value is all the same
>>> adam = paddle.optimizer.Adam(0.01, parameters = emb.parameters())
>>> for batch in range(10):
...     input = paddle.randint(low=0, high=5, shape=[5])
...     out = emb(input)
...     out.backward()
...     print("Learning rate of step{}: {}".format(batch, adam.get_lr())) # 0.01
...     adam.step()
Learning rate of step0: 0.01
Learning rate of step1: 0.01
Learning rate of step2: 0.01
Learning rate of step3: 0.01
Learning rate of step4: 0.01
Learning rate of step5: 0.01
Learning rate of step6: 0.01
Learning rate of step7: 0.01
Learning rate of step8: 0.01
Learning rate of step9: 0.01

>>> ## example2: StepDecay is used, return the scheduled learning rate
>>> scheduler = paddle.optimizer.lr.StepDecay(learning_rate=0.5, step_size=2, gamma=0.1)
>>> adam = paddle.optimizer.Adam(scheduler, parameters = emb.parameters())
>>> for batch in range(10):
...     input = paddle.randint(low=0, high=5, shape=[5])
...     out = emb(input)
...     out.backward()
...     print("Learning rate of step{}: {}".format(batch, adam.get_lr())) # 0.5->0.05...
...     adam.step()
...     scheduler.step()
Learning rate of step0: 0.5
Learning rate of step1: 0.5
Learning rate of step2: 0.05
Learning rate of step3: 0.05
Learning rate of step4: 0.005000000000000001
Learning rate of step5: 0.005000000000000001
Learning rate of step6: 0.0005000000000000001
Learning rate of step7: 0.0005000000000000001
Learning rate of step8: 5.000000000000001e-05
Learning rate of step9: 5.000000000000001e-05

>>> # train on static graph mode
>>> paddle.enable_static()
>>> main_prog = paddle.static.Program()
>>> start_prog = paddle.static.Program()
>>> with paddle.static.program_guard(main_prog, start_prog):
...     x = paddle.static.data(name='x', shape=[None, 10])
...     z = paddle.static.nn.fc(x, 100)
...     loss = paddle.mean(z)
...     scheduler = paddle.optimizer.lr.StepDecay(learning_rate=0.5, step_size=2, gamma=0.1)
...     adam = paddle.optimizer.Adam(learning_rate=scheduler)
...     adam.minimize(loss)

>>> exe = paddle.static.Executor()
>>> exe.run(start_prog)
>>> for batch in range(10):
...     print("Learning rate of step{}: {}".format(batch, adam.get_lr())) # 0.5->0.05->0.005...
...     out = exe.run(main_prog, feed={'x': np.random.randn(3, 10).astype('float32')})
...     scheduler.step()
Learning rate of step0: 0.5
Learning rate of step1: 0.5
Learning rate of step2: 0.05
Learning rate of step3: 0.05
Learning rate of step4: 0.005000000000000001
Learning rate of step5: 0.005000000000000001
Learning rate of step6: 0.0005000000000000001
Learning rate of step7: 0.0005000000000000001
Learning rate of step8: 5.000000000000001e-05
Learning rate of step9: 5.000000000000001e-05
set_lr ( value )

set_lr

Api_attr

imperative

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

Parameters

value (float) – the value of learning rate

Returns

None

Examples

>>> import paddle
>>> linear = paddle.nn.Linear(10, 10)

>>> adam = paddle.optimizer.Adam(0.1, parameters=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.get_lr()
...     print("current lr is {}".format(lr))
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_lr_scheduler ( scheduler )

set_lr_scheduler

Api_attr

imperative

Set the LRScheduler of the learning rate manually in the optimizer. If the optimizer already used LRScheduler previously, this API will set it be the new one.

Parameters

scheduler (LRScheduler) – the LRScheduler of learning rate

Returns

None

Examples

>>> import paddle
>>> linear = paddle.nn.Linear(10, 10)

>>> adam = paddle.optimizer.Adam(0.1, parameters=linear.parameters())

>>> # set learning rate manually by class LRScheduler
>>> scheduler = paddle.optimizer.lr.MultiStepDecay(learning_rate=0.5, milestones=[2,4,6], gamma=0.8)
>>> adam.set_lr_scheduler(scheduler)
>>> lr = adam.get_lr()
>>> print("current lr is {}".format(lr))
current lr is 0.5

>>> # set learning rate manually by another LRScheduler
>>> scheduler = paddle.optimizer.lr.StepDecay(learning_rate=0.1, step_size=5, gamma=0.6)
>>> adam.set_lr_scheduler(scheduler)
>>> lr = adam.get_lr()
>>> print("current lr is {}".format(lr))
current lr is 0.1
set_state_dict ( state_dict )

set_state_dict

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

Parameters

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

Returns

None

Examples

>>> import paddle

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

>>> layer_state_dict = emb.state_dict()
>>> paddle.save(layer_state_dict, "emb.pdparams")

>>> scheduler = paddle.optimizer.lr.NoamDecay(
...     d_model=0.01, warmup_steps=100, verbose=True)
>>> adam = paddle.optimizer.Adam(
...     learning_rate=scheduler,
...     parameters=emb.parameters())
>>> opt_state_dict = adam.state_dict()
>>> paddle.save(opt_state_dict, "adam.pdopt")

>>> opti_state_dict = paddle.load("adam.pdopt")
>>> adam.set_state_dict(opti_state_dict)
state_dict ( )

state_dict

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

Parameters

None

Returns

dict contains all the Tensor used by optimizer

Return type

state_dict(dict)

Examples

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

>>> adam = paddle.optimizer.Adam(0.001, parameters=emb.parameters())
>>> state_dict = adam.state_dict()