|---|
| [ View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/reduce_lr_on_plateau.py#L11-L153) |
Reduce learning rate when a metric has stopped improving.
Inherits From: [`Callback`](https://www.tensorflow.org/api_docs/python/tf/keras/callbacks/Callback)
tf.keras.callbacks.ReduceLROnPlateau(
monitor='val_loss',
factor=0.1,
patience=10,
verbose=0,
mode='auto',
min_delta=0.0001,
cooldown=0,
min_lr=0.0,
**kwargs
)
Models often benefit from reducing the learning rate by a factor
of 2-10 once learning stagnates. This callback monitors a
quantity and if no improvement is seen for a 'patience' number
of epochs, the learning rate is reduced.
#### Example:
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2,
patience=5, min_lr=0.001)
model.fit(x_train, y_train, callbacks=[reduce_lr])
| ## Args ||
|---|---|
| `monitor` | String. Quantity to be monitored. |
| `factor` | Float. Factor by which the learning rate will be reduced. `new_lr = lr * factor`. |
| `patience` | Integer. Number of epochs with no improvement after which learning rate will be reduced. |
| `verbose` | Integer. 0: quiet, 1: update messages. |
| `mode` | String. One of `{'auto', 'min', 'max'}`. In `'min'` mode, the learning rate will be reduced when the quantity monitored has stopped decreasing; in `'max'` mode it will be reduced when the quantity monitored has stopped increasing; in `'auto'` mode, the direction is automatically inferred from the name of the monitored quantity. |
| `min_delta` | Float. Threshold for measuring the new optimum, to only focus on significant changes. |
| `cooldown` | Integer. Number of epochs to wait before resuming normal operation after the learning rate has been reduced. |
| `min_lr` | Float. Lower bound on the learning rate. |
| ## Attributes ||
|---|---|
| `model` |
|
## Methods
### `in_cooldown`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/reduce_lr_on_plateau.py#L152-L153)
in_cooldown()
### `on_batch_begin`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L102-L104)
on_batch_begin(
batch, logs=None
)
A backwards compatibility alias for `on_train_batch_begin`.
### `on_batch_end`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L106-L108)
on_batch_end(
batch, logs=None
)
A backwards compatibility alias for `on_train_batch_end`.
### `on_epoch_begin`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L110-L121)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/reduce_lr_on_plateau.py#L99-L150)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L211-L225)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L227-L240)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L288-L297)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L299-L308)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L174-L191)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L193-L209)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L265-L274)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L276-L286)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L139-L155)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L157-L172)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/reduce_lr_on_plateau.py#L96-L97)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L253-L263)
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`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L74-L75)
set_model(
model
)
### `set_params`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/callbacks/callback.py#L71-L72)
set_params(
params
)