tf.keras.callbacks.SwapEMAWeights

Swaps model weights and EMA weights before and after evaluation.

Inherits From: Callback

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(...)]
)

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.

model

Methods

on_batch_begin

View source

A backwards compatibility alias for on_train_batch_begin.

on_batch_end

View source

A backwards compatibility alias for on_train_batch_end.

on_epoch_begin

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

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

View source

set_params

View source