# tf.keras.callbacks.ReduceLROnPlateau

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/keras/callbacks/ReduceLROnPlateau) | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L1797-L1916) |

Reduce learning rate when a metric has stopped improving.

Inherits From: [`Callback`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/keras/callbacks/Callback)

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.keras.callbacks.ReduceLROnPlateau`](https://www.tensorflow.org/api_docs/python/tf/keras/callbacks/ReduceLROnPlateau), \`tf.compat.v2.keras.callbacks.ReduceLROnPlateau\`

<br />

    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, **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])

<br />

<br />

<br />

| ## Arguments ||
|---|---|
| `monitor` | quantity to be monitored. |
| `factor` | factor by which the learning rate will be reduced. new_lr = lr \* factor |
| `patience` | number of epochs with no improvement after which learning rate will be reduced. |
| `verbose` | int. 0: quiet, 1: update messages. |
| `mode` | one of {auto, min, max}. In `min` mode, lr 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` | threshold for measuring the new optimum, to only focus on significant changes. |
| `cooldown` | number of epochs to wait before resuming normal operation after lr has been reduced. |
| `min_lr` | lower bound on the learning rate. |

<br />

## Methods

### `in_cooldown`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L1915-L1916)

    in_cooldown()

### `on_batch_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L465-L466)

    on_batch_begin(
        batch, logs=None
    )

A backwards compatibility alias for `on_train_batch_begin`.

### `on_batch_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L468-L469)

    on_batch_end(
        batch, logs=None
    )

A backwards compatibility alias for `on_train_batch_end`.

### `on_epoch_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L471-L481)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `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. |

<br />

### `on_epoch_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L1884-L1913)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `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_`. |

<br />

### `on_predict_batch_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L548-L557)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `batch` | integer, index of batch within the current epoch. |
| `logs` | dict. Has keys `batch` and `size` representing the current batch number and the size of the batch. |

<br />

### `on_predict_batch_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L559-L567)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `batch` | integer, index of batch within the current epoch. |
| `logs` | dict. Metric results for this batch. |

<br />

### `on_predict_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L609-L617)

    on_predict_begin(
        logs=None
    )

Called at the beginning of prediction.

Subclasses should override for any actions to run.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `logs` | dict. Currently no data is passed to this argument for this method but that may change in the future. |

<br />

### `on_predict_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L619-L627)

    on_predict_end(
        logs=None
    )

Called at the end of prediction.

Subclasses should override for any actions to run.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `logs` | dict. Currently no data is passed to this argument for this method but that may change in the future. |

<br />

### `on_test_batch_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L521-L533)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `batch` | integer, index of batch within the current epoch. |
| `logs` | dict. Has keys `batch` and `size` representing the current batch number and the size of the batch. |

<br />

### `on_test_batch_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L535-L546)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `batch` | integer, index of batch within the current epoch. |
| `logs` | dict. Metric results for this batch. |

<br />

### `on_test_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L589-L597)

    on_test_begin(
        logs=None
    )

Called at the beginning of evaluation or validation.

Subclasses should override for any actions to run.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `logs` | dict. Currently no data is passed to this argument for this method but that may change in the future. |

<br />

### `on_test_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L599-L607)

    on_test_end(
        logs=None
    )

Called at the end of evaluation or validation.

Subclasses should override for any actions to run.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `logs` | dict. Currently no data is passed to this argument for this method but that may change in the future. |

<br />

### `on_train_batch_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L496-L507)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `batch` | integer, index of batch within the current epoch. |
| `logs` | dict. Has keys `batch` and `size` representing the current batch number and the size of the batch. |

<br />

### `on_train_batch_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L509-L519)

    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.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `batch` | integer, index of batch within the current epoch. |
| `logs` | dict. Metric results for this batch. |

<br />

### `on_train_begin`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L1881-L1882)

    on_train_begin(
        logs=None
    )

Called at the beginning of training.

Subclasses should override for any actions to run.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `logs` | dict. Currently no data is passed to this argument for this method but that may change in the future. |

<br />

### `on_train_end`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L579-L587)

    on_train_end(
        logs=None
    )

Called at the end of training.

Subclasses should override for any actions to run.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `logs` | dict. Currently no data is passed to this argument for this method but that may change in the future. |

<br />

### `set_model`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L462-L463)

    set_model(
        model
    )

### `set_params`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/callbacks.py#L459-L460)

    set_params(
        params
    )