|---| | [ View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/layers/regularization/dropout.py#L6-L120) | Applies dropout to the input. Inherits From: [`Layer`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer), [`Operation`](https://www.tensorflow.org/api_docs/python/tf/keras/Operation) tf.keras.layers.Dropout( rate, noise_shape=None, seed=None, **kwargs ) ### Used in the notebooks | Used in the guide | Used in the tutorials | |---|---| | - [Effective Tensorflow 2](https://www.tensorflow.org/guide/effective_tf2) - [Migrate checkpoint saving](https://www.tensorflow.org/guide/migrate/checkpoint_saver) - [Migrate evaluation](https://www.tensorflow.org/guide/migrate/evaluator) - [Migrate the fault tolerance mechanism](https://www.tensorflow.org/guide/migrate/fault_tolerance) - [Migrate TensorBoard: TensorFlow's visualization toolkit](https://www.tensorflow.org/guide/migrate/tensorboard) | - [Overfit and underfit](https://www.tensorflow.org/tutorials/keras/overfit_and_underfit) - [Using DTensors with Keras](https://www.tensorflow.org/tutorials/distribute/dtensor_keras_tutorial) - [Simple audio recognition: Recognizing keywords](https://www.tensorflow.org/tutorials/audio/simple_audio) - [Deep Convolutional Generative Adversarial Network](https://www.tensorflow.org/tutorials/generative/dcgan) - [Basic text classification](https://www.tensorflow.org/tutorials/keras/text_classification) | The `Dropout` layer randomly sets input units to 0 with a frequency of `rate` at each step during training time, which helps prevent overfitting. Inputs not set to 0 are scaled up by `1 / (1 - rate)` such that the sum over all inputs is unchanged. Note that the `Dropout` layer only applies when `training` is set to `True` in `call()`, such that no values are dropped during inference. When using `model.fit`, `training` will be appropriately set to `True` automatically. In other contexts, you can set the argument explicitly to `True` when calling the layer. (This is in contrast to setting `trainable=False` for a `Dropout` layer. `trainable` does not affect the layer's behavior, as `Dropout` does not have any variables/weights that can be frozen during training.)


| ## Args || |---|---| | `rate` | Float between 0 and 1. Fraction of the input units to drop. | | `noise_shape` | 1D integer tensor representing the shape of the binary dropout mask that will be multiplied with the input. For instance, if your inputs have shape `(batch_size, timesteps, features)` and you want the dropout mask to be the same for all timesteps, you can use `noise_shape=(batch_size, 1, features)`. | | `seed` | A Python integer to use as random seed. |



| ## Call arguments || |---|---| | `inputs` | Input tensor (of any rank). | | `training` | Python boolean indicating whether the layer should behave in training mode (adding dropout) or in inference mode (doing nothing). |



| ## Attributes || |---|---| | `input` | Retrieves the input tensor(s) of a symbolic operation.
Only returns the tensor(s) corresponding to the *first time* the operation was called. | | `output` | Retrieves the output tensor(s) of a layer.
Only returns the tensor(s) corresponding to the *first time* the operation was called. |
## Methods ### `from_config` [View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/ops/operation.py#L322-L362) @classmethod from_config( config ) Creates an operation from its config. This method is the reverse of `get_config`, capable of instantiating the same operation from the config dictionary. > [!NOTE] > **Note:** If you override this method, you might receive a serialized dtype config, which is a `dict`. You can deserialize it as follows: if "dtype" in config and isinstance(config["dtype"], dict): policy = dtype_policies.deserialize(config["dtype"])


| Args || |---|---| | `config` | A Python dictionary, typically the output of `get_config`. |



| Returns || |---|---| | An operation instance. ||