# tf.keras.Model

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L65-L3144) |

`Model` groups layers into an object with training and inference features.

Inherits From: [`Layer`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/Module)

#### View aliases


**Main aliases**

[`tf.keras.models.Model`](https://www.tensorflow.org/api_docs/python/tf/keras/Model)
**Compat aliases for migration**

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

[`tf.compat.v1.keras.Model`](https://www.tensorflow.org/api_docs/python/tf/keras/Model), [`tf.compat.v1.keras.models.Model`](https://www.tensorflow.org/api_docs/python/tf/keras/Model)

<br />

    tf.keras.Model(
        *args, **kwargs
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `inputs` | The input(s) of the model: a [`keras.Input`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Input) object or list of [`keras.Input`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Input) objects. |
| `outputs` | The output(s) of the model. See Functional API example below. |
| `name` | String, the name of the model. |

<br />

There are two ways to instantiate a `Model`:

1 - With the "Functional API", where you start from `Input`,
you chain layer calls to specify the model's forward pass,
and finally you create your model from inputs and outputs:

    import tensorflow as tf

    inputs = tf.keras.Input(shape=(3,))
    x = tf.keras.layers.Dense(4, activation=tf.nn.relu)(inputs)
    outputs = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x)
    model = tf.keras.Model(inputs=inputs, outputs=outputs)

> [!NOTE]
> **Note:** Only dicts, lists, and tuples of input tensors are supported. Nested inputs are not supported (e.g. lists of list or dicts of dict).

A new Functional API model can also be created by using the
intermediate tensors. This enables you to quickly extract sub-components
of the model.

#### Example:

    inputs = keras.Input(shape=(None, None, 3))
    processed = keras.layers.RandomCrop(width=32, height=32)(inputs)
    conv = keras.layers.Conv2D(filters=2, kernel_size=3)(processed)
    pooling = keras.layers.GlobalAveragePooling2D()(conv)
    feature = keras.layers.Dense(10)(pooling)

    full_model = keras.Model(inputs, feature)
    backbone = keras.Model(processed, conv)
    activations = keras.Model(conv, feature)

Note that the `backbone` and `activations` models are not
created with [`keras.Input`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Input) objects, but with the tensors that are originated
from `keras.Inputs` objects. Under the hood, the layers and weights will
be shared across these models, so that user can train the `full_model`, and
use `backbone` or `activations` to do feature extraction.
The inputs and outputs of the model can be nested structures of tensors as
well, and the created models are standard Functional API models that support
all the existing APIs.

2 - By subclassing the `Model` class: in that case, you should define your
layers in `__init__()` and you should implement the model's forward pass
in `call()`.

    import tensorflow as tf

    class MyModel(tf.keras.Model):

      def __init__(self):
        super().__init__()
        self.dense1 = tf.keras.layers.Dense(4, activation=tf.nn.relu)
        self.dense2 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)

      def call(self, inputs):
        x = self.dense1(inputs)
        return self.dense2(x)

    model = MyModel()

If you subclass `Model`, you can optionally have
a `training` argument (boolean) in `call()`, which you can use to specify
a different behavior in training and inference:

    import tensorflow as tf

    class MyModel(tf.keras.Model):

      def __init__(self):
        super().__init__()
        self.dense1 = tf.keras.layers.Dense(4, activation=tf.nn.relu)
        self.dense2 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)
        self.dropout = tf.keras.layers.Dropout(0.5)

      def call(self, inputs, training=False):
        x = self.dense1(inputs)
        if training:
          x = self.dropout(x, training=training)
        return self.dense2(x)

    model = MyModel()

Once the model is created, you can config the model with losses and metrics
with `model.compile()`, train the model with `model.fit()`, or use the model
to do prediction with `model.predict()`.

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `distribute_strategy` | The [`tf.distribute.Strategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/Strategy) this model was created under. |
| `layers` | <br /> <br /> |
| `metrics_names` | Returns the model's display labels for all outputs. <br /> > [!NOTE] > **Note:** `metrics_names` are available only after a [`keras.Model`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model) has been trained/evaluated on actual data. inputs = tf.keras.layers.Input(shape=(3,)) outputs = tf.keras.layers.Dense(2)(inputs) model = tf.keras.models.Model(inputs=inputs, outputs=outputs) model.compile(optimizer="Adam", loss="mse", metrics=["mae"]) model.metrics_names [] x = np.random.random((2, 3)) y = np.random.randint(0, 2, (2, 2)) model.fit(x, y) model.metrics_names ['loss', 'mae'] inputs = tf.keras.layers.Input(shape=(3,)) d = tf.keras.layers.Dense(2, name='out') output_1 = d(inputs) output_2 = d(inputs) model = tf.keras.models.Model( inputs=inputs, outputs=[output_1, output_2]) model.compile(optimizer="Adam", loss="mse", metrics=["mae", "acc"]) model.fit(x, (y, y)) model.metrics_names ['loss', 'out_loss', 'out_1_loss', 'out_mae', 'out_acc', 'out_1_mae', 'out_1_acc'] <br /> |
| `run_eagerly` | Settable attribute indicating whether the model should run eagerly. <br /> Running eagerly means that your model will be run step by step, like Python code. Your model might run slower, but it should become easier for you to debug it by stepping into individual layer calls. By default, we will attempt to compile your model to a static graph to deliver the best execution performance. |

<br />

## Methods

### `call`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L450-L479)

    call(
        inputs, training=None, mask=None
    )

Calls the model on new inputs and returns the outputs as tensors.

In this case `call()` just reapplies
all ops in the graph to the new inputs
(e.g. build a new computational graph from the provided inputs).

> [!NOTE]
> **Note:** This method should not be called directly. It is only meant to be overridden when subclassing [`tf.keras.Model`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model). To call a model on an input, always use the `__call__()` method, i.e. `model(inputs)`, which relies on the underlying `call()` method.

<br />

<br />

<br />

| Args ||
|---|---|
| `inputs` | Input tensor, or dict/list/tuple of input tensors. |
| `training` | Boolean or boolean scalar tensor, indicating whether to run the `Network` in training mode or inference mode. |
| `mask` | A mask or list of masks. A mask can be either a boolean tensor or None (no mask). For more details, check the guide [here](https://www.tensorflow.org/guide/keras/masking_and_padding). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A tensor if there is a single output, or a list of tensors if there are more than one outputs. ||

<br />

### `compile`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L481-L617)

    compile(
        optimizer='rmsprop',
        loss=None,
        metrics=None,
        loss_weights=None,
        weighted_metrics=None,
        run_eagerly=None,
        steps_per_execution=None,
        jit_compile=None,
        **kwargs
    )

Configures the model for training.

#### Example:

    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-3),
                  loss=tf.keras.losses.BinaryCrossentropy(),
                  metrics=[tf.keras.metrics.BinaryAccuracy(),
                           tf.keras.metrics.FalseNegatives()])

<br />

<br />

<br />

| Args ||
|---|---|
| `optimizer` | String (name of optimizer) or optimizer instance. See [`tf.keras.optimizers`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/optimizers). |
| `loss` | Loss function. Maybe be a string (name of loss function), or a [`tf.keras.losses.Loss`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/losses/Loss) instance. See [`tf.keras.losses`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/losses). A loss function is any callable with the signature `loss = fn(y_true, y_pred)`, where `y_true` are the ground truth values, and `y_pred` are the model's predictions. `y_true` should have shape `(batch_size, d0, .. dN)` (except in the case of sparse loss functions such as sparse categorical crossentropy which expects integer arrays of shape `(batch_size, d0, .. dN-1)`). `y_pred` should have shape `(batch_size, d0, .. dN)`. The loss function should return a float tensor. If a custom `Loss` instance is used and reduction is set to `None`, return value has shape `(batch_size, d0, .. dN-1)` i.e. per-sample or per-timestep loss values; otherwise, it is a scalar. If the model has multiple outputs, you can use a different loss on each output by passing a dictionary or a list of losses. The loss value that will be minimized by the model will then be the sum of all individual losses, unless `loss_weights` is specified. |
| `metrics` | List of metrics to be evaluated by the model during training and testing. Each of this can be a string (name of a built-in function), function or a [`tf.keras.metrics.Metric`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/metrics/Metric) instance. See [`tf.keras.metrics`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/metrics). Typically you will use `metrics=['accuracy']`. A function is any callable with the signature `result = fn(y_true, y_pred)`. To specify different metrics for different outputs of a multi-output model, you could also pass a dictionary, such as `metrics={'output_a': 'accuracy', 'output_b': ['accuracy', 'mse']}`. You can also pass a list to specify a metric or a list of metrics for each output, such as `metrics=[['accuracy'], ['accuracy', 'mse']]` or `metrics=['accuracy', ['accuracy', 'mse']]`. When you pass the strings 'accuracy' or 'acc', we convert this to one of [`tf.keras.metrics.BinaryAccuracy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/metrics/BinaryAccuracy), [`tf.keras.metrics.CategoricalAccuracy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/metrics/CategoricalAccuracy), [`tf.keras.metrics.SparseCategoricalAccuracy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/metrics/SparseCategoricalAccuracy) based on the loss function used and the model output shape. We do a similar conversion for the strings 'crossentropy' and 'ce' as well. |
| `loss_weights` | Optional list or dictionary specifying scalar coefficients (Python floats) to weight the loss contributions of different model outputs. The loss value that will be minimized by the model will then be the *weighted sum* of all individual losses, weighted by the `loss_weights` coefficients. If a list, it is expected to have a 1:1 mapping to the model's outputs. If a dict, it is expected to map output names (strings) to scalar coefficients. |
| `weighted_metrics` | List of metrics to be evaluated and weighted by `sample_weight` or `class_weight` during training and testing. |
| `run_eagerly` | Bool. Defaults to `False`. If `True`, this `Model`'s logic will not be wrapped in a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). Recommended to leave this as `None` unless your `Model` cannot be run inside a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). `run_eagerly=True` is not supported when using [`tf.distribute.experimental.ParameterServerStrategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/experimental/ParameterServerStrategy). |
| `steps_per_execution` | Int. Defaults to 1. The number of batches to run during each [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) call. Running multiple batches inside a single [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) call can greatly improve performance on TPUs or small models with a large Python overhead. At most, one full epoch will be run each execution. If a number larger than the size of the epoch is passed, the execution will be truncated to the size of the epoch. Note that if `steps_per_execution` is set to `N`, [`Callback.on_batch_begin`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/Callback#on_batch_begin) and [`Callback.on_batch_end`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/Callback#on_batch_end) methods will only be called every `N` batches (i.e. before/after each [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) execution). |
| `jit_compile` | If `True`, compile the model training step with XLA. [XLA](https://www.tensorflow.org/xla) is an optimizing compiler for machine learning. `jit_compile` is not enabled for by default. This option cannot be enabled with `run_eagerly=True`. Note that `jit_compile=True` is may not necessarily work for all models. For more information on supported operations please refer to the [XLA documentation](https://www.tensorflow.org/xla). Also refer to [known XLA issues](https://www.tensorflow.org/xla/known_issues) for more details. |
| `**kwargs` | Arguments supported for backwards compatibility only. |

<br />

### `compute_loss`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L866-L919)

    compute_loss(
        x=None, y=None, y_pred=None, sample_weight=None
    )

Compute the total loss, validate it, and return it.

Subclasses can optionally override this method to provide custom loss
computation logic.

#### Example:

    class MyModel(tf.keras.Model):

      def __init__(self, *args, **kwargs):
        super(MyModel, self).__init__(*args, **kwargs)
        self.loss_tracker = tf.keras.metrics.Mean(name='loss')

      def compute_loss(self, x, y, y_pred, sample_weight):
        loss = tf.reduce_mean(tf.math.squared_difference(y_pred, y))
        loss += tf.add_n(self.losses)
        self.loss_tracker.update_state(loss)
        return loss

      def reset_metrics(self):
        self.loss_tracker.reset_states()

      @property
      def metrics(self):
        return [self.loss_tracker]

    tensors = tf.random.uniform((10, 10)), tf.random.uniform((10,))
    dataset = tf.data.Dataset.from_tensor_slices(tensors).repeat().batch(1)

    inputs = tf.keras.layers.Input(shape=(10,), name='my_input')
    outputs = tf.keras.layers.Dense(10)(inputs)
    model = MyModel(inputs, outputs)
    model.add_loss(tf.reduce_sum(outputs))

    optimizer = tf.keras.optimizers.SGD()
    model.compile(optimizer, loss='mse', steps_per_execution=10)
    model.fit(dataset, epochs=2, steps_per_epoch=10)
    print('My custom loss: ', model.loss_tracker.result().numpy())

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input data. |
| `y` | Target data. |
| `y_pred` | Predictions returned by the model (output of `model(x)`) |
| `sample_weight` | Sample weights for weighting the loss function. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The total loss as a [`tf.Tensor`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/Tensor), or `None` if no loss results (which is the case when called by [`Model.test_step`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#test_step)). ||

<br />

### `compute_metrics`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L921-L966)

    compute_metrics(
        x, y, y_pred, sample_weight
    )

Update metric states and collect all metrics to be returned.

Subclasses can optionally override this method to provide custom metric
updating and collection logic.

#### Example:

    class MyModel(tf.keras.Sequential):

      def compute_metrics(self, x, y, y_pred, sample_weight):

        # This super call updates `self.compiled_metrics` and returns results
        # for all metrics listed in `self.metrics`.
        metric_results = super(MyModel, self).compute_metrics(
            x, y, y_pred, sample_weight)

        # Note that `self.custom_metric` is not listed in `self.metrics`.
        self.custom_metric.update_state(x, y, y_pred, sample_weight)
        metric_results['custom_metric_name'] = self.custom_metric.result()
        return metric_results

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input data. |
| `y` | Target data. |
| `y_pred` | Predictions returned by the model (output of `model.call(x)`) |
| `sample_weight` | Sample weights for weighting the loss function. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `dict` containing values that will be passed to [`tf.keras.callbacks.CallbackList.on_train_batch_end()`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/CallbackList#on_train_batch_end). Typically, the values of the metrics listed in `self.metrics` are returned. Example: `{'loss': 0.2, 'accuracy': 0.7}`. ||

<br />

### `evaluate`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L1570-L1728)

    evaluate(
        x=None,
        y=None,
        batch_size=None,
        verbose=1,
        sample_weight=None,
        steps=None,
        callbacks=None,
        max_queue_size=10,
        workers=1,
        use_multiprocessing=False,
        return_dict=False,
        **kwargs
    )

Returns the loss value \& metrics values for the model in test mode.

Computation is done in batches (see the `batch_size` arg.)

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input data. It could be: <br /> - A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs). - A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs). - A dict mapping input names to the corresponding array/tensors, if the model has named inputs. - A [`tf.data`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data) dataset. Should return a tuple of either `(inputs, targets)` or `(inputs, targets, sample_weights)`. - A generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) returning `(inputs, targets)` or `(inputs, targets, sample_weights)`. A more detailed description of unpacking behavior for iterator types (Dataset, generator, Sequence) is given in the `Unpacking behavior for iterator-like inputs` section of `Model.fit`. |
| `y` | Target data. Like the input data `x`, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent with `x` (you cannot have Numpy inputs and tensor targets, or inversely). If `x` is a dataset, generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instance, `y` should not be specified (since targets will be obtained from the iterator/dataset). |
| `batch_size` | Integer or `None`. Number of samples per batch of computation. If unspecified, `batch_size` will default to 32. Do not specify the `batch_size` if your data is in the form of a dataset, generators, or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instances (since they generate batches). |
| `verbose` | 0 or 1. Verbosity mode. 0 = silent, 1 = progress bar. |
| `sample_weight` | Optional Numpy array of weights for the test samples, used for weighting the loss function. You can either pass a flat (1D) Numpy array with the same length as the input samples (1:1 mapping between weights and samples), or in the case of temporal data, you can pass a 2D array with shape `(samples, sequence_length)`, to apply a different weight to every timestep of every sample. This argument is not supported when `x` is a dataset, instead pass sample weights as the third element of `x`. |
| `steps` | Integer or `None`. Total number of steps (batches of samples) before declaring the evaluation round finished. Ignored with the default value of `None`. If x is a [`tf.data`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data) dataset and `steps` is None, 'evaluate' will run until the dataset is exhausted. This argument is not supported with array inputs. |
| `callbacks` | List of [`keras.callbacks.Callback`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/Callback) instances. List of callbacks to apply during evaluation. See [callbacks](https://www.tensorflow.org/api_docs/python/tf/keras/callbacks). |
| `max_queue_size` | Integer. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. Maximum size for the generator queue. If unspecified, `max_queue_size` will default to 10. |
| `workers` | Integer. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. Maximum number of processes to spin up when using process-based threading. If unspecified, `workers` will default to 1. |
| `use_multiprocessing` | Boolean. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. If `True`, use process-based threading. If unspecified, `use_multiprocessing` will default to `False`. Note that because this implementation relies on multiprocessing, you should not pass non-picklable arguments to the generator as they can't be passed easily to children processes. |
| `return_dict` | If `True`, loss and metric results are returned as a dict, with each key being the name of the metric. If `False`, they are returned as a list. |
| `**kwargs` | Unused at this time. |

See the discussion of `Unpacking behavior for iterator-like inputs` for
[`Model.fit`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#fit).

<br />

<br />

<br />

| Returns ||
|---|---|
| Scalar test loss (if the model has a single output and no metrics) or list of scalars (if the model has multiple outputs and/or metrics). The attribute `model.metrics_names` will give you the display labels for the scalar outputs. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | If `model.evaluate` is wrapped in a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). |

<br />

### `fit`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L1069-L1444)

    fit(
        x=None,
        y=None,
        batch_size=None,
        epochs=1,
        verbose='auto',
        callbacks=None,
        validation_split=0.0,
        validation_data=None,
        shuffle=True,
        class_weight=None,
        sample_weight=None,
        initial_epoch=0,
        steps_per_epoch=None,
        validation_steps=None,
        validation_batch_size=None,
        validation_freq=1,
        max_queue_size=10,
        workers=1,
        use_multiprocessing=False
    )

Trains the model for a fixed number of epochs (iterations on a dataset).

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input data. It could be: <br /> - A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs). - A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs). - A dict mapping input names to the corresponding array/tensors, if the model has named inputs. - A [`tf.data`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data) dataset. Should return a tuple of either `(inputs, targets)` or `(inputs, targets, sample_weights)`. - A generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) returning `(inputs, targets)` or `(inputs, targets, sample_weights)`. - A [`tf.keras.utils.experimental.DatasetCreator`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/experimental/DatasetCreator), which wraps a callable that takes a single argument of type [`tf.distribute.InputContext`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/InputContext), and returns a [`tf.data.Dataset`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data/Dataset). `DatasetCreator` should be used when users prefer to specify the per-replica batching and sharding logic for the `Dataset`. See [`tf.keras.utils.experimental.DatasetCreator`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/experimental/DatasetCreator) doc for more information. A more detailed description of unpacking behavior for iterator types (Dataset, generator, Sequence) is given below. If using [`tf.distribute.experimental.ParameterServerStrategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/experimental/ParameterServerStrategy), only `DatasetCreator` type is supported for `x`. |
| `y` | Target data. Like the input data `x`, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent with `x` (you cannot have Numpy inputs and tensor targets, or inversely). If `x` is a dataset, generator, or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instance, `y` should not be specified (since targets will be obtained from `x`). |
| `batch_size` | Integer or `None`. Number of samples per gradient update. If unspecified, `batch_size` will default to 32. Do not specify the `batch_size` if your data is in the form of datasets, generators, or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instances (since they generate batches). |
| `epochs` | Integer. Number of epochs to train the model. An epoch is an iteration over the entire `x` and `y` data provided (unless the `steps_per_epoch` flag is set to something other than None). Note that in conjunction with `initial_epoch`, `epochs` is to be understood as "final epoch". The model is not trained for a number of iterations given by `epochs`, but merely until the epoch of index `epochs` is reached. |
| `verbose` | 'auto', 0, 1, or 2. Verbosity mode. 0 = silent, 1 = progress bar, 2 = one line per epoch. 'auto' defaults to 1 for most cases, but 2 when used with `ParameterServerStrategy`. Note that the progress bar is not particularly useful when logged to a file, so verbose=2 is recommended when not running interactively (eg, in a production environment). |
| `callbacks` | List of [`keras.callbacks.Callback`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/Callback) instances. List of callbacks to apply during training. See [`tf.keras.callbacks`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks). Note [`tf.keras.callbacks.ProgbarLogger`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/ProgbarLogger) and [`tf.keras.callbacks.History`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/History) callbacks are created automatically and need not be passed into `model.fit`. [`tf.keras.callbacks.ProgbarLogger`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/ProgbarLogger) is created or not based on `verbose` argument to `model.fit`. Callbacks with batch-level calls are currently unsupported with [`tf.distribute.experimental.ParameterServerStrategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/experimental/ParameterServerStrategy), and users are advised to implement epoch-level calls instead with an appropriate `steps_per_epoch` value. |
| `validation_split` | Float between 0 and 1. Fraction of the training data to be used as validation data. The model will set apart this fraction of the training data, will not train on it, and will evaluate the loss and any model metrics on this data at the end of each epoch. The validation data is selected from the last samples in the `x` and `y` data provided, before shuffling. This argument is not supported when `x` is a dataset, generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instance. `validation_split` is not yet supported with [`tf.distribute.experimental.ParameterServerStrategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/experimental/ParameterServerStrategy). |
| `validation_data` | Data on which to evaluate the loss and any model metrics at the end of each epoch. The model will not be trained on this data. Thus, note the fact that the validation loss of data provided using `validation_split` or `validation_data` is not affected by regularization layers like noise and dropout. `validation_data` will override `validation_split`. `validation_data` could be: - A tuple `(x_val, y_val)` of Numpy arrays or tensors. - A tuple `(x_val, y_val, val_sample_weights)` of NumPy arrays. - A [`tf.data.Dataset`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data/Dataset). - A Python generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) returning `(inputs, targets)` or `(inputs, targets, sample_weights)`. `validation_data` is not yet supported with [`tf.distribute.experimental.ParameterServerStrategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/experimental/ParameterServerStrategy). |
| `shuffle` | Boolean (whether to shuffle the training data before each epoch) or str (for 'batch'). This argument is ignored when `x` is a generator or an object of tf.data.Dataset. 'batch' is a special option for dealing with the limitations of HDF5 data; it shuffles in batch-sized chunks. Has no effect when `steps_per_epoch` is not `None`. |
| `class_weight` | Optional dictionary mapping class indices (integers) to a weight (float) value, used for weighting the loss function (during training only). This can be useful to tell the model to "pay more attention" to samples from an under-represented class. |
| `sample_weight` | Optional Numpy array of weights for the training samples, used for weighting the loss function (during training only). You can either pass a flat (1D) Numpy array with the same length as the input samples (1:1 mapping between weights and samples), or in the case of temporal data, you can pass a 2D array with shape `(samples, sequence_length)`, to apply a different weight to every timestep of every sample. This argument is not supported when `x` is a dataset, generator, or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instance, instead provide the sample_weights as the third element of `x`. |
| `initial_epoch` | Integer. Epoch at which to start training (useful for resuming a previous training run). |
| `steps_per_epoch` | Integer or `None`. Total number of steps (batches of samples) before declaring one epoch finished and starting the next epoch. When training with input tensors such as TensorFlow data tensors, the default `None` is equal to the number of samples in your dataset divided by the batch size, or 1 if that cannot be determined. If x is a [`tf.data`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data) dataset, and 'steps_per_epoch' is None, the epoch will run until the input dataset is exhausted. When passing an infinitely repeating dataset, you must specify the `steps_per_epoch` argument. If `steps_per_epoch=-1` the training will run indefinitely with an infinitely repeating dataset. This argument is not supported with array inputs. When using [`tf.distribute.experimental.ParameterServerStrategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/experimental/ParameterServerStrategy): - `steps_per_epoch=None` is not supported. |
| `validation_steps` | Only relevant if `validation_data` is provided and is a [`tf.data`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data) dataset. Total number of steps (batches of samples) to draw before stopping when performing validation at the end of every epoch. If 'validation_steps' is None, validation will run until the `validation_data` dataset is exhausted. In the case of an infinitely repeated dataset, it will run into an infinite loop. If 'validation_steps' is specified and only part of the dataset will be consumed, the evaluation will start from the beginning of the dataset at each epoch. This ensures that the same validation samples are used every time. |
| `validation_batch_size` | Integer or `None`. Number of samples per validation batch. If unspecified, will default to `batch_size`. Do not specify the `validation_batch_size` if your data is in the form of datasets, generators, or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instances (since they generate batches). |
| `validation_freq` | Only relevant if validation data is provided. Integer or `collections.abc.Container` instance (e.g. list, tuple, etc.). If an integer, specifies how many training epochs to run before a new validation run is performed, e.g. `validation_freq=2` runs validation every 2 epochs. If a Container, specifies the epochs on which to run validation, e.g. `validation_freq=[1, 2, 10]` runs validation at the end of the 1st, 2nd, and 10th epochs. |
| `max_queue_size` | Integer. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. Maximum size for the generator queue. If unspecified, `max_queue_size` will default to 10. |
| `workers` | Integer. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. Maximum number of processes to spin up when using process-based threading. If unspecified, `workers` will default to 1. |
| `use_multiprocessing` | Boolean. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. If `True`, use process-based threading. If unspecified, `use_multiprocessing` will default to `False`. Note that because this implementation relies on multiprocessing, you should not pass non-picklable arguments to the generator as they can't be passed easily to children processes. |

Unpacking behavior for iterator-like inputs:
A common pattern is to pass a tf.data.Dataset, generator, or
tf.keras.utils.Sequence to the `x` argument of fit, which will in fact
yield not only features (x) but optionally targets (y) and sample weights.
Keras requires that the output of such iterator-likes be unambiguous. The
iterator should return a tuple of length 1, 2, or 3, where the optional
second and third elements will be used for y and sample_weight
respectively. Any other type provided will be wrapped in a length one
tuple, effectively treating everything as 'x'. When yielding dicts, they
should still adhere to the top-level tuple structure.
e.g. `({"x0": x0, "x1": x1}, y)`. Keras will not attempt to separate
features, targets, and weights from the keys of a single dict.
A notable unsupported data type is the namedtuple. The reason is that
it behaves like both an ordered datatype (tuple) and a mapping
datatype (dict). So given a namedtuple of the form:
`namedtuple("example_tuple", ["y", "x"])`
it is ambiguous whether to reverse the order of the elements when
interpreting the value. Even worse is a tuple of the form:
`namedtuple("other_tuple", ["x", "y", "z"])`
where it is unclear if the tuple was intended to be unpacked into x, y,
and sample_weight or passed through as a single element to `x`. As a
result the data processing code will simply raise a ValueError if it
encounters a namedtuple. (Along with instructions to remedy the issue.)

<br />

<br />

<br />

| Returns ||
|---|---|
| A `History` object. Its `History.history` attribute is a record of training loss values and metrics values at successive epochs, as well as validation loss values and validation metrics values (if applicable). ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | <br /> 1. If the model was never compiled or, 2. If `model.fit` is wrapped in [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). |
| `ValueError` | In case of mismatch between the provided input data and what the model expects or when the input data is empty. |

### `get_layer`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2797-L2831)

    get_layer(
        name=None, index=None
    )

Retrieves a layer based on either its name (unique) or index.

If `name` and `index` are both provided, `index` will take precedence.
Indices are based on order of horizontal graph traversal (bottom-up).

<br />

<br />

<br />

| Args ||
|---|---|
| `name` | String, name of layer. |
| `index` | Integer, index of layer. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A layer instance. ||

<br />

### `load_weights`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2505-L2610)

    load_weights(
        filepath, by_name=False, skip_mismatch=False, options=None
    )

Loads all layer weights, either from a TensorFlow or an HDF5 weight file.

If `by_name` is False weights are loaded based on the network's
topology. This means the architecture should be the same as when the weights
were saved. Note that layers that don't have weights are not taken into
account in the topological ordering, so adding or removing layers is fine as
long as they don't have weights.

If `by_name` is True, weights are loaded into layers only if they share the
same name. This is useful for fine-tuning or transfer-learning models where
some of the layers have changed.

Only topological loading (`by_name=False`) is supported when loading weights
from the TensorFlow format. Note that topological loading differs slightly
between TensorFlow and HDF5 formats for user-defined classes inheriting from
[`tf.keras.Model`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model): HDF5 loads based on a flattened list of weights, while the
TensorFlow format loads based on the object-local names of attributes to
which layers are assigned in the `Model`'s constructor.

<br />

<br />

<br />

| Args ||
|---|---|
| `filepath` | String, path to the weights file to load. For weight files in TensorFlow format, this is the file prefix (the same as was passed to `save_weights`). This can also be a path to a SavedModel saved from `model.save`. |
| `by_name` | Boolean, whether to load weights by name or by topological order. Only topological loading is supported for weight files in TensorFlow format. |
| `skip_mismatch` | Boolean, whether to skip loading of layers where there is a mismatch in the number of weights, or a mismatch in the shape of the weight (only valid when `by_name=True`). |
| `options` | Optional [`tf.train.CheckpointOptions`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/CheckpointOptions) object that specifies options for loading weights. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| When loading a weight file in TensorFlow format, returns the same status object as [`tf.train.Checkpoint.restore`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint#restore). When graph building, restore ops are run automatically as soon as the network is built (on first call for user-defined classes inheriting from `Model`, immediately if it is already built). <br /> When loading weights in HDF5 format, returns `None`. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ImportError` | If `h5py` is not available and the weight file is in HDF5 format. |
| `ValueError` | If `skip_mismatch` is set to `True` when `by_name` is `False`. |

<br />

### `make_predict_function`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L1753-L1823)

    make_predict_function(
        force=False
    )

Creates a function that executes one step of inference.

This method can be overridden to support custom inference logic.
This method is called by [`Model.predict`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#predict) and [`Model.predict_on_batch`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#predict_on_batch).

Typically, this method directly controls [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) and
[`tf.distribute.Strategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/Strategy) settings, and delegates the actual evaluation
logic to [`Model.predict_step`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#predict_step).

This function is cached the first time [`Model.predict`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#predict) or
[`Model.predict_on_batch`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#predict_on_batch) is called. The cache is cleared whenever
[`Model.compile`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#compile) is called. You can skip the cache and generate again the
function with `force=True`.

<br />

<br />

<br />

| Args ||
|---|---|
| `force` | Whether to regenerate the predict function and skip the cached function if available. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Function. The function created by this method should accept a [`tf.data.Iterator`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data/Iterator), and return the outputs of the `Model`. ||

<br />

### `make_test_function`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L1476-L1568)

    make_test_function(
        force=False
    )

Creates a function that executes one step of evaluation.

This method can be overridden to support custom evaluation logic.
This method is called by [`Model.evaluate`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#evaluate) and [`Model.test_on_batch`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#test_on_batch).

Typically, this method directly controls [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) and
[`tf.distribute.Strategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/Strategy) settings, and delegates the actual evaluation
logic to [`Model.test_step`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#test_step).

This function is cached the first time [`Model.evaluate`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#evaluate) or
[`Model.test_on_batch`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#test_on_batch) is called. The cache is cleared whenever
[`Model.compile`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#compile) is called. You can skip the cache and generate again the
function with `force=True`.

<br />

<br />

<br />

| Args ||
|---|---|
| `force` | Whether to regenerate the test function and skip the cached function if available. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Function. The function created by this method should accept a [`tf.data.Iterator`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data/Iterator), and return a `dict` containing values that will be passed to `tf.keras.Callbacks.on_test_batch_end`. ||

<br />

### `make_train_function`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L968-L1067)

    make_train_function(
        force=False
    )

Creates a function that executes one step of training.

This method can be overridden to support custom training logic.
This method is called by [`Model.fit`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#fit) and [`Model.train_on_batch`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#train_on_batch).

Typically, this method directly controls [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) and
[`tf.distribute.Strategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/Strategy) settings, and delegates the actual training
logic to [`Model.train_step`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#train_step).

This function is cached the first time [`Model.fit`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#fit) or
[`Model.train_on_batch`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#train_on_batch) is called. The cache is cleared whenever
[`Model.compile`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#compile) is called. You can skip the cache and generate again the
function with `force=True`.

<br />

<br />

<br />

| Args ||
|---|---|
| `force` | Whether to regenerate the train function and skip the cached function if available. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Function. The function created by this method should accept a [`tf.data.Iterator`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data/Iterator), and return a `dict` containing values that will be passed to `tf.keras.Callbacks.on_train_batch_end`, such as `{'loss': 0.2, 'accuracy': 0.7}`. ||

<br />

### `predict`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L1825-L2012)

    predict(
        x,
        batch_size=None,
        verbose=0,
        steps=None,
        callbacks=None,
        max_queue_size=10,
        workers=1,
        use_multiprocessing=False
    )

Generates output predictions for the input samples.

Computation is done in batches. This method is designed for batch processing
of large numbers of inputs. It is not intended for use inside of loops
that iterate over your data and process small numbers of inputs at a time.

For small numbers of inputs that fit in one batch,
directly use `__call__()` for faster execution, e.g.,
`model(x)`, or `model(x, training=False)` if you have layers such as
[`tf.keras.layers.BatchNormalization`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/layers/BatchNormalization) that behave differently during
inference. You may pair the individual model call with a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function)
for additional performance inside your inner loop.
If you need access to numpy array values instead of tensors after your
model call, you can use `tensor.numpy()` to get the numpy array value of
an eager tensor.

Also, note the fact that test loss is not affected by
regularization layers like noise and dropout.

> [!NOTE]
> **Note:** See [this FAQ entry](https://keras.io/getting_started/faq/#whats-the-difference-between-model-methods-predict-and-call) for more details about the difference between `Model` methods `predict()` and `__call__()`.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input samples. It could be: <br /> - A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs). - A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs). - A [`tf.data`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data) dataset. - A generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instance. A more detailed description of unpacking behavior for iterator types (Dataset, generator, Sequence) is given in the `Unpacking behavior for iterator-like inputs` section of `Model.fit`. |
| `batch_size` | Integer or `None`. Number of samples per batch. If unspecified, `batch_size` will default to 32. Do not specify the `batch_size` if your data is in the form of dataset, generators, or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) instances (since they generate batches). |
| `verbose` | Verbosity mode, 0 or 1. |
| `steps` | Total number of steps (batches of samples) before declaring the prediction round finished. Ignored with the default value of `None`. If x is a [`tf.data`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/data) dataset and `steps` is None, `predict()` will run until the input dataset is exhausted. |
| `callbacks` | List of [`keras.callbacks.Callback`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/Callback) instances. List of callbacks to apply during prediction. See [callbacks](https://www.tensorflow.org/api_docs/python/tf/keras/callbacks). |
| `max_queue_size` | Integer. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. Maximum size for the generator queue. If unspecified, `max_queue_size` will default to 10. |
| `workers` | Integer. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. Maximum number of processes to spin up when using process-based threading. If unspecified, `workers` will default to 1. |
| `use_multiprocessing` | Boolean. Used for generator or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/utils/Sequence) input only. If `True`, use process-based threading. If unspecified, `use_multiprocessing` will default to `False`. Note that because this implementation relies on multiprocessing, you should not pass non-picklable arguments to the generator as they can't be passed easily to children processes. |

See the discussion of `Unpacking behavior for iterator-like inputs` for
[`Model.fit`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#fit). Note that Model.predict uses the same interpretation rules as
[`Model.fit`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#fit) and [`Model.evaluate`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#evaluate), so inputs must be unambiguous for all
three methods.

<br />

<br />

<br />

| Returns ||
|---|---|
| Numpy array(s) of predictions. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | If `model.predict` is wrapped in a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). |
| `ValueError` | In case of mismatch between the provided input data and the model's expectations, or in case a stateful model receives a number of samples that is not a multiple of the batch size. |

<br />

### `predict_on_batch`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2158-L2180)

    predict_on_batch(
        x
    )

Returns predictions for a single batch of samples.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input data. It could be: <br /> - A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs). - A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs). |

<br />

<br />

<br />

| Returns ||
|---|---|
| Numpy array(s) of predictions. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | If `model.predict_on_batch` is wrapped in a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). |

<br />

### `predict_step`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L1730-L1751)

    predict_step(
        data
    )

The logic for one inference step.

This method can be overridden to support custom inference logic.
This method is called by [`Model.make_predict_function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#make_predict_function).

This method should contain the mathematical logic for one step of inference.
This typically includes the forward pass.

Configuration details for *how* this logic is run (e.g. [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) and
[`tf.distribute.Strategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/Strategy) settings), should be left to
[`Model.make_predict_function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#make_predict_function), which can also be overridden.

<br />

<br />

<br />

| Args ||
|---|---|
| `data` | A nested structure of `Tensor`s. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The result of one inference step, typically the output of calling the `Model` on data. ||

<br />

### `reset_metrics`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2014-L2034)

    reset_metrics()

Resets the state of all the metrics in the model.

#### Examples:

    inputs = tf.keras.layers.Input(shape=(3,))
    outputs = tf.keras.layers.Dense(2)(inputs)
    model = tf.keras.models.Model(inputs=inputs, outputs=outputs)
    model.compile(optimizer="Adam", loss="mse", metrics=["mae"])

    x = np.random.random((2, 3))
    y = np.random.randint(0, 2, (2, 2))
    _ = model.fit(x, y, verbose=0)
    assert all(float(m.result()) for m in model.metrics)

    model.reset_metrics()
    assert all(float(m.result()) == 0 for m in model.metrics)

### `reset_states`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2694-L2697)

    reset_states()

### `save`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2332-L2385)

    save(
        filepath,
        overwrite=True,
        include_optimizer=True,
        save_format=None,
        signatures=None,
        options=None,
        save_traces=True
    )

Saves the model to Tensorflow SavedModel or a single HDF5 file.

Please see [`tf.keras.models.save_model`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/models/save_model) or the
[Serialization and Saving guide](https://keras.io/guides/serialization_and_saving/)
for details.

<br />

<br />

<br />

| Args ||
|---|---|
| `filepath` | String, PathLike, path to SavedModel or H5 file to save the model. |
| `overwrite` | Whether to silently overwrite any existing file at the target location, or provide the user with a manual prompt. |
| `include_optimizer` | If True, save optimizer's state together. |
| `save_format` | Either `'tf'` or `'h5'`, indicating whether to save the model to Tensorflow SavedModel or HDF5. Defaults to 'tf' in TF 2.X, and 'h5' in TF 1.X. |
| `signatures` | Signatures to save with the SavedModel. Applicable to the 'tf' format only. Please see the `signatures` argument in [`tf.saved_model.save`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/saved_model/save) for details. |
| `options` | (only applies to SavedModel format) [`tf.saved_model.SaveOptions`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/saved_model/SaveOptions) object that specifies options for saving to SavedModel. |
| `save_traces` | (only applies to SavedModel format) When enabled, the SavedModel will store the function traces for each layer. This can be disabled, so that only the configs of each layer are stored. Defaults to `True`. Disabling this will decrease serialization time and reduce file size, but it requires that all custom layers/models implement a `get_config()` method. |

<br />

#### Example:

    from keras.models import load_model

    model.save('my_model.h5')  # creates a HDF5 file 'my_model.h5'
    del model  # deletes the existing model

    # returns a compiled model
    # identical to the previous one
    model = load_model('my_model.h5')

### `save_spec`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2871-L2908)

    save_spec(
        dynamic_batch=True
    )

Returns the [`tf.TensorSpec`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/TensorSpec) of call inputs as a tuple `(args, kwargs)`.

This value is automatically defined after calling the model for the first
time. Afterwards, you can use it when exporting the model for serving:

    model = tf.keras.Model(...)

    @tf.function
    def serve(*args, **kwargs):
      outputs = model(*args, **kwargs)
      # Apply postprocessing steps, or add additional outputs.
      ...
      return outputs

    # arg_specs is `[tf.TensorSpec(...), ...]`. kwarg_specs, in this example, is
    # an empty dict since functional models do not use keyword arguments.
    arg_specs, kwarg_specs = model.save_spec()

    model.save(path, signatures={
      'serving_default': serve.get_concrete_function(*arg_specs, **kwarg_specs)
    })

<br />

<br />

<br />

| Args ||
|---|---|
| `dynamic_batch` | Whether to set the batch sizes of all the returned [`tf.TensorSpec`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/TensorSpec) to `None`. (Note that when defining functional or Sequential models with `tf.keras.Input([...], batch_size=X)`, the batch size will always be preserved). Defaults to `True`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| If the model inputs are defined, returns a tuple `(args, kwargs)`. All elements in `args` and `kwargs` are [`tf.TensorSpec`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/TensorSpec). If the model inputs are not defined, returns `None`. The model inputs are automatically set when calling the model, `model.fit`, `model.evaluate` or `model.predict`. ||

<br />

### `save_weights`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2387-L2503)

    save_weights(
        filepath, overwrite=True, save_format=None, options=None
    )

Saves all layer weights.

Either saves in HDF5 or in TensorFlow format based on the `save_format`
argument.

When saving in HDF5 format, the weight file has:

- `layer_names` (attribute), a list of strings (ordered names of model layers).
- For every layer, a `group` named `layer.name`
  - For every such layer group, a group attribute `weight_names`, a list of strings (ordered names of weights tensor of the layer).
  - For every weight in the layer, a dataset storing the weight value, named after the weight tensor.

When saving in TensorFlow format, all objects referenced by the network are
saved in the same format as [`tf.train.Checkpoint`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint), including any `Layer`
instances or `Optimizer` instances assigned to object attributes. For
networks constructed from inputs and outputs using `tf.keras.Model(inputs,
outputs)`, `Layer` instances used by the network are tracked/saved
automatically. For user-defined classes which inherit from [`tf.keras.Model`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model),
`Layer` instances must be assigned to object attributes, typically in the
constructor. See the documentation of [`tf.train.Checkpoint`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint) and
[`tf.keras.Model`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model) for details.

While the formats are the same, do not mix `save_weights` and
[`tf.train.Checkpoint`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint). Checkpoints saved by [`Model.save_weights`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#save_weights) should be
loaded using [`Model.load_weights`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#load_weights). Checkpoints saved using
[`tf.train.Checkpoint.save`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint#save) should be restored using the corresponding
[`tf.train.Checkpoint.restore`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint#restore). Prefer [`tf.train.Checkpoint`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint) over
`save_weights` for training checkpoints.

The TensorFlow format matches objects and variables by starting at a root
object, `self` for `save_weights`, and greedily matching attribute
names. For [`Model.save`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#save) this is the `Model`, and for [`Checkpoint.save`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint#save) this
is the `Checkpoint` even if the `Checkpoint` has a model attached. This
means saving a [`tf.keras.Model`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model) using `save_weights` and loading into a
[`tf.train.Checkpoint`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/Checkpoint) with a `Model` attached (or vice versa) will not match
the `Model`'s variables. See the
[guide to training checkpoints](https://www.tensorflow.org/guide/checkpoint)
for details on the TensorFlow format.

<br />

<br />

<br />

| Args ||
|---|---|
| `filepath` | String or PathLike, path to the file to save the weights to. When saving in TensorFlow format, this is the prefix used for checkpoint files (multiple files are generated). Note that the '.h5' suffix causes weights to be saved in HDF5 format. |
| `overwrite` | Whether to silently overwrite any existing file at the target location, or provide the user with a manual prompt. |
| `save_format` | Either 'tf' or 'h5'. A `filepath` ending in '.h5' or '.keras' will default to HDF5 if `save_format` is `None`. Otherwise `None` defaults to 'tf'. |
| `options` | Optional [`tf.train.CheckpointOptions`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/train/CheckpointOptions) object that specifies options for saving weights. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ImportError` | If `h5py` is not available when attempting to save in HDF5 format. |

<br />

### `summary`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2747-L2785)

    summary(
        line_length=None,
        positions=None,
        print_fn=None,
        expand_nested=False,
        show_trainable=False
    )

Prints a string summary of the network.

<br />

<br />

<br />

| Args ||
|---|---|
| `line_length` | Total length of printed lines (e.g. set this to adapt the display to different terminal window sizes). |
| `positions` | Relative or absolute positions of log elements in each line. If not provided, defaults to `[.33, .55, .67, 1.]`. |
| `print_fn` | Print function to use. Defaults to `print`. It will be called on each line of the summary. You can set it to a custom function in order to capture the string summary. |
| `expand_nested` | Whether to expand the nested models. If not provided, defaults to `False`. |
| `show_trainable` | Whether to show if a layer is trainable. If not provided, defaults to `False`. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | if `summary()` is called before the model is built. |

<br />

### `test_on_batch`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2101-L2156)

    test_on_batch(
        x, y=None, sample_weight=None, reset_metrics=True, return_dict=False
    )

Test the model on a single batch of samples.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input data. It could be: <br /> - A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs). - A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs). - A dict mapping input names to the corresponding array/tensors, if the model has named inputs. |
| `y` | Target data. Like the input data `x`, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent with `x` (you cannot have Numpy inputs and tensor targets, or inversely). |
| `sample_weight` | Optional array of the same length as x, containing weights to apply to the model's loss for each sample. In the case of temporal data, you can pass a 2D array with shape (samples, sequence_length), to apply a different weight to every timestep of every sample. |
| `reset_metrics` | If `True`, the metrics returned will be only for this batch. If `False`, the metrics will be statefully accumulated across batches. |
| `return_dict` | If `True`, loss and metric results are returned as a dict, with each key being the name of the metric. If `False`, they are returned as a list. |

<br />

<br />

<br />

| Returns ||
|---|---|
| Scalar test loss (if the model has a single output and no metrics) or list of scalars (if the model has multiple outputs and/or metrics). The attribute `model.metrics_names` will give you the display labels for the scalar outputs. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | If `model.test_on_batch` is wrapped in a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). |

<br />

### `test_step`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L1446-L1474)

    test_step(
        data
    )

The logic for one evaluation step.

This method can be overridden to support custom evaluation logic.
This method is called by [`Model.make_test_function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#make_test_function).

This function should contain the mathematical logic for one step of
evaluation.
This typically includes the forward pass, loss calculation, and metrics
updates.

Configuration details for *how* this logic is run (e.g. [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) and
[`tf.distribute.Strategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/Strategy) settings), should be left to
[`Model.make_test_function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#make_test_function), which can also be overridden.

<br />

<br />

<br />

| Args ||
|---|---|
| `data` | A nested structure of `Tensor`s. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `dict` containing values that will be passed to [`tf.keras.callbacks.CallbackList.on_train_batch_end`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/CallbackList#on_train_batch_end). Typically, the values of the `Model`'s metrics are returned. ||

<br />

### `to_json`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2649-L2664)

    to_json(
        **kwargs
    )

Returns a JSON string containing the network configuration.

To load a network from a JSON save file, use
[`keras.models.model_from_json(json_string, custom_objects={})`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/models/model_from_json).

<br />

<br />

<br />

| Args ||
|---|---|
| `**kwargs` | Additional keyword arguments to be passed to `json.dumps()`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A JSON string. ||

<br />

### `to_yaml`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2666-L2692)

    to_yaml(
        **kwargs
    )

Returns a yaml string containing the network configuration.

> [!NOTE]
> **Note:** Since TF 2.6, this method is no longer supported and will raise a RuntimeError.

To load a network from a yaml save file, use
[`keras.models.model_from_yaml(yaml_string, custom_objects={})`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/models/model_from_yaml).

`custom_objects` should be a dictionary mapping
the names of custom losses / layers / etc to the corresponding
functions / classes.

<br />

<br />

<br />

| Args ||
|---|---|
| `**kwargs` | Additional keyword arguments to be passed to `yaml.dump()`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A YAML string. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | announces that the method poses a security risk |

<br />

### `train_on_batch`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L2036-L2099)

    train_on_batch(
        x,
        y=None,
        sample_weight=None,
        class_weight=None,
        reset_metrics=True,
        return_dict=False
    )

Runs a single gradient update on a single batch of data.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | Input data. It could be: <br /> - A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs). - A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs). - A dict mapping input names to the corresponding array/tensors, if the model has named inputs. |
| `y` | Target data. Like the input data `x`, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent with `x` (you cannot have Numpy inputs and tensor targets, or inversely). |
| `sample_weight` | Optional array of the same length as x, containing weights to apply to the model's loss for each sample. In the case of temporal data, you can pass a 2D array with shape (samples, sequence_length), to apply a different weight to every timestep of every sample. |
| `class_weight` | Optional dictionary mapping class indices (integers) to a weight (float) to apply to the model's loss for the samples from this class during training. This can be useful to tell the model to "pay more attention" to samples from an under-represented class. |
| `reset_metrics` | If `True`, the metrics returned will be only for this batch. If `False`, the metrics will be statefully accumulated across batches. |
| `return_dict` | If `True`, loss and metric results are returned as a dict, with each key being the name of the metric. If `False`, they are returned as a list. |

<br />

<br />

<br />

| Returns ||
|---|---|
| Scalar training loss (if the model has a single output and no metrics) or list of scalars (if the model has multiple outputs and/or metrics). The attribute `model.metrics_names` will give you the display labels for the scalar outputs. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | If `model.train_on_batch` is wrapped in a [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function). |

<br />

### `train_step`

[View source](https://github.com/keras-team/keras/tree/v2.8.0/keras/engine/training.py#L831-L864)

    train_step(
        data
    )

The logic for one training step.

This method can be overridden to support custom training logic.
For concrete examples of how to override this method see
[Customizing what happends in fit](https://www.tensorflow.org/guide/keras/customizing_what_happens_in_fit).
This method is called by [`Model.make_train_function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#make_train_function).

This method should contain the mathematical logic for one step of training.
This typically includes the forward pass, loss calculation, backpropagation,
and metric updates.

Configuration details for *how* this logic is run (e.g. [`tf.function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/function) and
[`tf.distribute.Strategy`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/distribute/Strategy) settings), should be left to
[`Model.make_train_function`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/Model#make_train_function), which can also be overridden.

<br />

<br />

<br />

| Args ||
|---|---|
| `data` | A nested structure of `Tensor`s. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `dict` containing values that will be passed to [`tf.keras.callbacks.CallbackList.on_train_batch_end`](https://www.tensorflow.org/versions/r2.8/api_docs/python/tf/keras/callbacks/CallbackList#on_train_batch_end). Typically, the values of the `Model`'s metrics are returned. Example: `{'loss': 0.2, 'accuracy': 0.7}`. ||

<br />