tfa.optimizers.SGDW

View source on GitHub

Optimizer that implements the Momentum algorithm with weight_decay.

Inherits From: DecoupledWeightDecayExtension

This is an implementation of the SGDW optimizer described in "Decoupled Weight Decay Regularization" by Loshchilov & Hutter (https://arxiv.org/abs/1711.05101) ([pdf])(https://arxiv.org/pdf/1711.05101.pdf). It computes the update step of tf.keras.optimizers.SGD and additionally decays the variable. Note that this is different from adding L2 regularization on the variables to the loss. Decoupling the weight decay from other hyperparameters (in particular the learning rate) simplifies hyperparameter search.

For further information see the documentation of the SGD Optimizer.

This optimizer can also be instantiated as

extend_with_decoupled_weight_decay(tf.keras.optimizers.SGD,
                                   weight_decay=weight_decay)
step = tf.Variable(0, trainable=False)
schedule = tf.optimizers.schedules.PiecewiseConstantDecay(
    [10000, 15000], [1e-0, 1e-1, 1e-2])
# lr and wd can be a function or a tensor
lr = 1e-1 * schedule(step)
wd = lambda: 1e-4 * schedule(step)

# ...

optimizer = tfa.optimizers.SGDW(
    learning_rate=lr, weight_decay=wd, momentum=0.9)

learning_rate float hyperparameter >= 0. Learning rate.
momentum float hyperparameter >= 0 that accelerates SGD in the relevant direction and dampens oscillations.
nesterov boolean. Whether to apply Nesterov momentum.
name Optional name prefix for the operations created when applying gradients. Defaults to 'SGD'.
**kwargs keyword arguments. Allowed to be {clipnorm, clipvalue, lr, decay}. clipnorm is clip gradients by norm; clipvalue is clip gradients by value, decay is included for backward compatibility to allow time inverse decay of learning rate. lr is included for backward compatibility, recommended to use learning_rate instead.

iterations Variable. The number of training steps this Optimizer has run.
weights Returns variables of this Optimizer based on the order created.

Methods

add_slot

Add a new slot variable for var.

add_weight

apply_gradients

View source

Apply gradients to variables.

This is the second part of minimize(). It returns an Operation that applies gradients.

Args
grads_and_vars List of (gradient, variable) pairs.
name Optional name for the returned operation. Default to the name passed to the Optimizer constructor.
decay_var_list Optional list of variables to be decayed. Defaults to all variables in var_list.
**kwargs Additional arguments to pass to the base optimizer's apply_gradient method, e.g., TF2.2 added an argument experimental_aggregate_gradients.

Returns
An Operation that applies the specified gradients.

Raises
TypeError If grads_and_vars is malformed.
ValueError If none of the variables have gradients.

from_config

View source

Creates an optimizer from its config.

This method is the reverse of get_config, capable of instantiating the same optimizer from the config dictionary.

Arguments
config A Python dictionary, typically the output of get_config.
custom_objects A Python dictionary mapping names to additional Python objects used to create this optimizer, such as a function used for a hyperparameter.

Returns
An optimizer instance.

get_config

View source

get_gradients

Returns gradients of loss with respect to params.

Arguments
loss Loss tensor.
params List of variables.

Returns
List of gradient tensors.

Raises
ValueError In case any gradient cannot be computed (e.g. if gradient function not implemented).

get_slot

get_slot_names

A list of names for this optimizer's slots.

get_updates

get_weights

Returns the current weights of the optimizer.

The weights of an optimizer are its state (ie, variables). This function returns the weight values associated with this optimizer as a list of Numpy arrays. The first value is always the iterations count of the optimizer, followed by the optimizer's state variables in the order they were created. The returned list can in turn be used to load state into similarly parameterized optimizers.

For example, the RMSprop optimizer for this simple model returns a list of three values-- the iteration count, followed by the root-mean-square value of the kernel and bias of the single Dense layer:

opt = tf.keras.optimizers.RMSprop()
m = tf.keras.models.Sequential([tf.keras.layers.Dense(10)])
m.compile(opt, loss='mse')
data = np.arange(100).reshape(5, 20)
labels = np.zeros(5)
print('Training'); results = m.fit(data, labels)
Training ...
len(opt.get_weights())
3

Returns
Weights values as a list of numpy arrays.

minimize

View source

Minimize loss by updating var_list.

This method simply computes gradient using tf.GradientTape and calls apply_gradients(). If you want to process the gradient before applying then call tf.GradientTape and apply_gradients() explicitly instead of using this function.

Args
loss A callable taking no arguments which returns the value to minimize.
var_list list or tuple of Variable objects to update to minimize loss, or a callable returning the list or tuple of Variable objects. Use callable when the variable list would otherwise be incomplete before minimize since the variables are created at the first time loss is called.
grad_loss Optional. A Tensor holding the gradient computed for loss.
decay_var_list Optional list of variables to be decayed. Defaults to all variables in var_list.
name Optional name for the returned operation.

Returns
An Operation that updates the variables in var_list.

Raises
ValueError If some of the variables are not Variable objects.

set_weights

Set the weights of the optimizer.

The weights of an optimizer are its state (ie, variables). This function takes the weight values associated with this optimizer as a list of Numpy arrays. The first value is always the iterations count of the optimizer, followed by the optimizer's state variables in the order they are created. The passed values are used to set the new state of the optimizer.

For example, the RMSprop optimizer for this simple model takes a list of three values-- the iteration count, followed by the root-mean-square value of the kernel and bias of the single Dense layer:

opt = tf.keras.optimizers.RMSprop()
m = tf.keras.models.Sequential([tf.keras.layers.Dense(10)])
m.compile(opt, loss='mse')
data = np.arange(100).reshape(5, 20)
labels = np.zeros(5)
print('Training'); results = m.fit(data, labels)
Training ...
new_weights = [np.array(10), np.ones([20, 10]), np.zeros([10])]
opt.set_weights(new_weights)
opt.iterations
<tf.Variable 'RMSprop/iter:0' shape=() dtype=int64, numpy=10>

Arguments
weights weight values as a list of numpy arrays.

variables

Returns variables of this Optimizer based on the order created.