# tf.keras.layers.SeparableConv2D

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/convolutional/separable_conv2d.py#L31-L211) |

Depthwise separable 2D convolution.

Inherits From: [`Layer`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Module)

#### View aliases


**Main aliases**

[`tf.keras.layers.SeparableConvolution2D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv2D)
**Compat aliases for migration**

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

\`tf.compat.v1.keras.layers.SeparableConv2D\`, \`tf.compat.v1.keras.layers.SeparableConvolution2D\`

<br />

    tf.keras.layers.SeparableConv2D(
        filters,
        kernel_size,
        strides=(1, 1),
        padding='valid',
        data_format=None,
        dilation_rate=(1, 1),
        depth_multiplier=1,
        activation=None,
        use_bias=True,
        depthwise_initializer='glorot_uniform',
        pointwise_initializer='glorot_uniform',
        bias_initializer='zeros',
        depthwise_regularizer=None,
        pointwise_regularizer=None,
        bias_regularizer=None,
        activity_regularizer=None,
        depthwise_constraint=None,
        pointwise_constraint=None,
        bias_constraint=None,
        **kwargs
    )

Separable convolutions consist of first performing
a depthwise spatial convolution
(which acts on each input channel separately)
followed by a pointwise convolution which mixes the resulting
output channels. The `depth_multiplier` argument controls how many
output channels are generated per input channel in the depthwise step.

Intuitively, separable convolutions can be understood as
a way to factorize a convolution kernel into two smaller kernels,
or as an extreme version of an Inception block.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `filters` | Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution). |
| `kernel_size` | An integer or tuple/list of 2 integers, specifying the height and width of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions. |
| `strides` | An integer or tuple/list of 2 integers, specifying the strides of the convolution along the height and width. Can be a single integer to specify the same value for all spatial dimensions. Current implementation only supports equal length strides in the row and column dimensions. Specifying any stride value != 1 is incompatible with specifying any `dilation_rate` value != 1. |
| `padding` | one of `"valid"` or `"same"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding with zeros evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. |
| `data_format` | A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch_size, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch_size, channels, height, width)`. When unspecified, uses `image_data_format` value found in your Keras config file at `~/.keras/keras.json` (if exists) else 'channels_last'. Defaults to 'channels_last'. |
| `dilation_rate` | An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. |
| `depth_multiplier` | The number of depthwise convolution output channels for each input channel. The total number of depthwise convolution output channels will be equal to `filters_in * depth_multiplier`. |
| `activation` | Activation function to use. If you don't specify anything, no activation is applied (see [`keras.activations`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/activations)). |
| `use_bias` | Boolean, whether the layer uses a bias vector. |
| `depthwise_initializer` | An initializer for the depthwise convolution kernel (see [`keras.initializers`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/initializers)). If None, then the default initializer ('glorot_uniform') will be used. |
| `pointwise_initializer` | An initializer for the pointwise convolution kernel (see [`keras.initializers`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/initializers)). If None, then the default initializer ('glorot_uniform') will be used. |
| `bias_initializer` | An initializer for the bias vector. If None, the default initializer ('zeros') will be used (see [`keras.initializers`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/initializers)). |
| `depthwise_regularizer` | Regularizer function applied to the depthwise kernel matrix (see [`keras.regularizers`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/regularizers)). |
| `pointwise_regularizer` | Regularizer function applied to the pointwise kernel matrix (see [`keras.regularizers`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/regularizers)). |
| `bias_regularizer` | Regularizer function applied to the bias vector (see [`keras.regularizers`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/regularizers)). |
| `activity_regularizer` | Regularizer function applied to the output of the layer (its "activation") (see [`keras.regularizers`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/regularizers)). |
| `depthwise_constraint` | Constraint function applied to the depthwise kernel matrix (see [`keras.constraints`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/constraints)). |
| `pointwise_constraint` | Constraint function applied to the pointwise kernel matrix (see [`keras.constraints`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/constraints)). |
| `bias_constraint` | Constraint function applied to the bias vector (see [`keras.constraints`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/constraints)). |

<br />

<br />

<br />

<br />

| ## Input shape ||
|---|---|
| 4D tensor with shape: `(batch_size, channels, rows, cols)` if data_format='channels_first' or 4D tensor with shape: `(batch_size, rows, cols, channels)` if data_format='channels_last'. ||

<br />

<br />

<br />

<br />

| ## Output shape ||
|---|---|
| 4D tensor with shape: `(batch_size, filters, new_rows, new_cols)` if data_format='channels_first' or 4D tensor with shape: `(batch_size, new_rows, new_cols, filters)` if data_format='channels_last'. `rows` and `cols` values might have changed due to padding. ||

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A tensor of rank 4 representing `activation(separableconv2d(inputs, kernel) + bias)`. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | if `padding` is "causal". |

<br />

## Methods

### `convolution_op`

[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/convolutional/base_conv.py#L254-L270)

    convolution_op(
        inputs, kernel
    )