<br />

<button value="stable" default="">See Stable</button> <button value="nightly">See Nightly</button>

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L1173-L1271) |

Computes the crossentropy loss between the labels and predictions.

Inherits From: [`Loss`](https://www.tensorflow.org/api_docs/python/tf/keras/Loss.md.txt)

```python
tf.keras.losses.SparseCategoricalCrossentropy(
    from_logits=False,
    ignore_class=None,
    reduction='sum_over_batch_size',
    axis=-1,
    name='sparse_categorical_crossentropy',
    dtype=None
)
```

### Used in the notebooks

| Used in the guide | Used in the tutorials |
|---|---|
| - [Effective Tensorflow 2](https://www.tensorflow.org/guide/effective_tf2.md.txt) - [Migrate early stopping](https://www.tensorflow.org/guide/migrate/early_stopping.md.txt) - [Migrate the fault tolerance mechanism](https://www.tensorflow.org/guide/migrate/fault_tolerance.md.txt) - [Use TPUs](https://www.tensorflow.org/guide/tpu.md.txt) - [tf.data: Build TensorFlow input pipelines](https://www.tensorflow.org/guide/data.md.txt) | - [Load text](https://www.tensorflow.org/tutorials/load_data/text.md.txt) - [Distributed training with Keras](https://www.tensorflow.org/tutorials/distribute/keras.md.txt) - [Image segmentation](https://www.tensorflow.org/tutorials/images/segmentation.md.txt) - [Save and load a model using a distribution strategy](https://www.tensorflow.org/tutorials/distribute/save_and_load.md.txt) - [Image classification](https://www.tensorflow.org/tutorials/images/classification.md.txt) |

Use this crossentropy loss function when there are two or more label
classes. We expect labels to be provided as integers. If you want to
provide labels using `one-hot` representation, please use
`CategoricalCrossentropy` loss. There should be `# classes` floating point
values per feature for `y_pred` and a single floating point value per
feature for `y_true`.

In the snippet below, there is a single floating point value per example for
`y_true` and `num_classes` floating pointing values per example for
`y_pred`. The shape of `y_true` is `[batch_size]` and the shape of `y_pred`
is `[batch_size, num_classes]`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `from_logits` | Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. |
| `reduction` | Type of reduction to apply to the loss. In almost all cases this should be `"sum_over_batch_size"`. Supported options are `"sum"`, `"sum_over_batch_size"`, `"mean"`, `"mean_with_sample_weight"` or `None`. `"sum"` sums the loss, `"sum_over_batch_size"` and `"mean"` sum the loss and divide by the sample size, and `"mean_with_sample_weight"` sums the loss and divides by the sum of the sample weights. `"none"` and `None` perform no aggregation. Defaults to `"sum_over_batch_size"`. |
| `axis` | The axis along which to compute crossentropy (the features axis). Defaults to `-1`. |
| `name` | Optional name for the loss instance. |
| `dtype` | The dtype of the loss's computations. Defaults to `None`, which means using [`keras.backend.floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/floatx.md.txt). [`keras.backend.floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/floatx.md.txt) is a `"float32"` unless set to different value (via [`keras.backend.set_floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/set_floatx.md.txt)). If a [`keras.DTypePolicy`](https://www.tensorflow.org/api_docs/python/tf/keras/DTypePolicy.md.txt) is provided, then the `compute_dtype` will be utilized. |

<br />

#### Examples:

```python
y_true = np.array([1, 2])
y_pred = np.array([[0.05, 0.95, 0], [0.1, 0.8, 0.1]])
# Using 'auto'/'sum_over_batch_size' reduction type.
scce = keras.losses.SparseCategoricalCrossentropy()
scce(y_true, y_pred)
1.177
```

```python
# Calling with 'sample_weight'.
scce(y_true, y_pred, sample_weight=np.array([0.3, 0.7]))
0.814
```

```python
# Using 'sum' reduction type.
scce = keras.losses.SparseCategoricalCrossentropy(
    reduction="sum")
scce(y_true, y_pred)
2.354
```

```python
# Using 'none' reduction type.
scce = keras.losses.SparseCategoricalCrossentropy(
    reduction=None)
scce(y_true, y_pred)
array([0.0513, 2.303], dtype=float32)
```

Usage with the `compile()` API:

```python
model.compile(optimizer='sgd',
              loss=keras.losses.SparseCategoricalCrossentropy())
```

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `dtype` | <br /> <br /> |

<br />

## Methods

### `call`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L28-L34)

```python
call(
    y_true, y_pred
)
```

### `from_config`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L42-L46)

```python
@classmethod
from_config(
    config
)
```

### `get_config`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/losses.py#L1263-L1271)

```python
get_config()
```

### `__call__`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/losses/loss.py#L56-L85)

```python
__call__(
    y_true, y_pred, sample_weight=None
)
```

Call self as a function.