TensorFlow is back at Google I/O on May 14! Register now

tf.keras.callbacks.SwapEMAWeights

View source on GitHub

Swaps model weights and EMA weights before and after evaluation.

Inherits From: Callback

tf.keras.callbacks.SwapEMAWeights(
    swap_on_epoch=False
)

This callbacks replaces the model's weight values with the values of the optimizer's EMA weights (the exponential moving average of the past model weights values, implementing "Polyak averaging") before model evaluation, and restores the previous weights after evaluation.

The SwapEMAWeights callback is to be used in conjunction with an optimizer that sets use_ema=True.

Note that the weights are swapped in-place in order to save memory. The behavior is undefined if you modify the EMA weights or model weights in other callbacks.

Example:

# Remember to set `use_ema=True` in the optimizer
optimizer = SGD(use_ema=True)
model.compile(optimizer=optimizer, loss=..., metrics=...)

# Metrics will be computed with EMA weights
model.fit(X_train, Y_train, callbacks=[SwapEMAWeights()])

# If you want to save model checkpoint with EMA weights, you can set
# `swap_on_epoch=True` and place ModelCheckpoint after SwapEMAWeights.
model.fit(
    X_train,
    Y_train,
    callbacks=[SwapEMAWeights(swap_on_epoch=True), ModelCheckpoint(...)]
)

Args
`swap_on_epoch`	whether to perform swapping at `on_epoch_begin()` and `on_epoch_end()`. This is useful if you want to use EMA weights for other callbacks such as `ModelCheckpoint`. Defaults to `False`.

Attributes

model

Methods

`on_batch_begin`

on_batch_begin(
    batch, logs=None
)

A backwards compatibility alias for on_train_batch_begin.

`on_batch_end`

on_batch_end(
    batch, logs=None
)

A backwards compatibility alias for on_train_batch_end.

`on_epoch_begin`

on_epoch_begin(
    epoch, logs=None
)

Called at the start of an epoch.

Subclasses should override for any actions to run. This function should only be called during TRAIN mode.

Args
`epoch`	Integer, index of epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_epoch_end`

on_epoch_end(
    epoch, logs=None
)

Called at the end of an epoch.

Subclasses should override for any actions to run. This function should only be called during TRAIN mode.

Args
`epoch`	Integer, index of epoch.
`logs`	Dict, metric results for this training epoch, and for the validation epoch if validation is performed. Validation result keys are prefixed with `val_`. For training epoch, the values of the `Model`'s metrics are returned. Example: `{'loss': 0.2, 'accuracy': 0.7}`.

`on_predict_batch_begin`

on_predict_batch_begin(
    batch, logs=None
)

Called at the beginning of a batch in predict methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_predict_batch_end`

on_predict_batch_end(
    batch, logs=None
)

Called at the end of a batch in predict methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Aggregated metric results up until this batch.

`on_predict_begin`

on_predict_begin(
    logs=None
)

Called at the beginning of prediction.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_predict_end`

on_predict_end(
    logs=None
)

Called at the end of prediction.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_test_batch_begin`

on_test_batch_begin(
    batch, logs=None
)

Called at the beginning of a batch in evaluate methods.

Also called at the beginning of a validation batch in the fit methods, if validation data is provided.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_test_batch_end`

on_test_batch_end(
    batch, logs=None
)

Called at the end of a batch in evaluate methods.

Also called at the end of a validation batch in the fit methods, if validation data is provided.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Aggregated metric results up until this batch.

`on_test_begin`

on_test_begin(
    logs=None
)

Called at the beginning of evaluation or validation.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_test_end`

on_test_end(
    logs=None
)

Called at the end of evaluation or validation.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently the output of the last call to `on_test_batch_end()` is passed to this argument for this method but that may change in the future.

`on_train_batch_begin`

on_train_batch_begin(
    batch, logs=None
)

Called at the beginning of a training batch in fit methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_train_batch_end`

on_train_batch_end(
    batch, logs=None
)

Called at the end of a training batch in fit methods.

Subclasses should override for any actions to run.

Note that if the steps_per_execution argument to compile in Model is set to N, this method will only be called every N batches.

Args
`batch`	Integer, index of batch within the current epoch.
`logs`	Dict. Aggregated metric results up until this batch.

`on_train_begin`

on_train_begin(
    logs=None
)

Called at the beginning of training.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently no data is passed to this argument for this method but that may change in the future.

`on_train_end`

on_train_end(
    logs=None
)

Called at the end of training.

Subclasses should override for any actions to run.

Args
`logs`	Dict. Currently the output of the last call to `on_epoch_end()` is passed to this argument for this method but that may change in the future.

`set_model`

set_model(
    model
)

`set_params`

set_params(
    params
)

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-27 UTC.