Depthwise convolution is a type of convolution in which each input channel is convolved with a different kernel (called a depthwise kernel). You can understand depthwise convolution as the first step in a depthwise separable convolution.

It is implemented via the following steps:

Split the input into individual channels.

Convolve each channel with an individual depthwise kernel with

`depth_multiplier`

output channels.Concatenate the convolved outputs along the channels axis.

Unlike a regular 2D convolution, depthwise convolution does not mix information across different input channels.

The `depth_multiplier`

argument determines how many filters are applied to
one input channel. As such, it controls the amount of output channels that
are generated per input channel in the depthwise step.

## Usage

```
layer_depthwise_conv_2d(
object,
kernel_size,
strides = list(1L, 1L),
padding = "valid",
depth_multiplier = 1L,
data_format = NULL,
dilation_rate = list(1L, 1L),
activation = NULL,
use_bias = TRUE,
depthwise_initializer = "glorot_uniform",
bias_initializer = "zeros",
depthwise_regularizer = NULL,
bias_regularizer = NULL,
activity_regularizer = NULL,
depthwise_constraint = NULL,
bias_constraint = NULL,
...
)
```

## Arguments

- object
Object to compose the layer with. A tensor, array, or sequential model.

- kernel_size
int or list of 2 integer, specifying the size of the depthwise convolution window.

- strides
int or list of 2 integer, specifying the stride length of the depthwise convolution.

`strides > 1`

is incompatible with`dilation_rate > 1`

.- padding
string, either

`"valid"`

or`"same"`

(case-insensitive).`"valid"`

means no padding.`"same"`

results in padding evenly to the left/right or up/down of the input. When`padding="same"`

and`strides=1`

, the output has the same size as the input.- 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

`input_channel * depth_multiplier`

.- data_format
string, either

`"channels_last"`

or`"channels_first"`

. The ordering of the dimensions in the inputs.`"channels_last"`

corresponds to inputs with shape`(batch, height, width, channels)`

while`"channels_first"`

corresponds to inputs with shape`(batch, channels, height, width)`

. It defaults to the`image_data_format`

value found in your Keras config file at`~/.keras/keras.json`

. If you never set it, then it will be`"channels_last"`

.- dilation_rate
int or list of 2 integers, specifying the dilation rate to use for dilated convolution.

- activation
Activation function. If

`NULL`

, no activation is applied.- use_bias
bool, if

`TRUE`

, bias will be added to the output.- depthwise_initializer
Initializer for the convolution kernel. If

`NULL`

, the default initializer (`"glorot_uniform"`

) will be used.- bias_initializer
Initializer for the bias vector. If

`NULL`

, the default initializer (`"zeros"`

) will be used.- depthwise_regularizer
Optional regularizer for the convolution kernel.

- bias_regularizer
Optional regularizer for the bias vector.

- activity_regularizer
Optional regularizer function for the output.

- depthwise_constraint
Optional projection function to be applied to the kernel after being updated by an

`Optimizer`

(e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training.- bias_constraint
Optional projection function to be applied to the bias after being updated by an

`Optimizer`

.- ...
For forward/backward compatability.

## Input Shape

If

`data_format="channels_last"`

: A 4D tensor with shape:`(batch_size, height, width, channels)`

If

`data_format="channels_first"`

: A 4D tensor with shape:`(batch_size, channels, height, width)`

## Output Shape

If

`data_format="channels_last"`

: A 4D tensor with shape:`(batch_size, new_height, new_width, channels * depth_multiplier)`

If

`data_format="channels_first"`

: A 4D tensor with shape:`(batch_size, channels * depth_multiplier, new_height, new_width)`

## Example

```
x <- random_uniform(c(4, 10, 10, 12))
y <- x |> layer_depthwise_conv_2d(3, 3, activation = 'relu')
shape(y)
```

## See also

Other convolutional layers: `layer_conv_1d()`

`layer_conv_1d_transpose()`

`layer_conv_2d()`

`layer_conv_2d_transpose()`

`layer_conv_3d()`

`layer_conv_3d_transpose()`

`layer_depthwise_conv_1d()`

`layer_separable_conv_1d()`

`layer_separable_conv_2d()`

Other layers: `Layer()`

`layer_activation()`

`layer_activation_elu()`

`layer_activation_leaky_relu()`

`layer_activation_parametric_relu()`

`layer_activation_relu()`

`layer_activation_softmax()`

`layer_activity_regularization()`

`layer_add()`

`layer_additive_attention()`

`layer_alpha_dropout()`

`layer_attention()`

`layer_average()`

`layer_average_pooling_1d()`

`layer_average_pooling_2d()`

`layer_average_pooling_3d()`

`layer_batch_normalization()`

`layer_bidirectional()`

`layer_category_encoding()`

`layer_center_crop()`

`layer_concatenate()`

`layer_conv_1d()`

`layer_conv_1d_transpose()`

`layer_conv_2d()`

`layer_conv_2d_transpose()`

`layer_conv_3d()`

`layer_conv_3d_transpose()`

`layer_conv_lstm_1d()`

`layer_conv_lstm_2d()`

`layer_conv_lstm_3d()`

`layer_cropping_1d()`

`layer_cropping_2d()`

`layer_cropping_3d()`

`layer_dense()`

`layer_depthwise_conv_1d()`

`layer_discretization()`

`layer_dot()`

`layer_dropout()`

`layer_einsum_dense()`

`layer_embedding()`

`layer_feature_space()`

`layer_flatten()`

`layer_flax_module_wrapper()`

`layer_gaussian_dropout()`

`layer_gaussian_noise()`

`layer_global_average_pooling_1d()`

`layer_global_average_pooling_2d()`

`layer_global_average_pooling_3d()`

`layer_global_max_pooling_1d()`

`layer_global_max_pooling_2d()`

`layer_global_max_pooling_3d()`

`layer_group_normalization()`

`layer_group_query_attention()`

`layer_gru()`

`layer_hashed_crossing()`

`layer_hashing()`

`layer_identity()`

`layer_integer_lookup()`

`layer_jax_model_wrapper()`

`layer_lambda()`

`layer_layer_normalization()`

`layer_lstm()`

`layer_masking()`

`layer_max_pooling_1d()`

`layer_max_pooling_2d()`

`layer_max_pooling_3d()`

`layer_maximum()`

`layer_mel_spectrogram()`

`layer_minimum()`

`layer_multi_head_attention()`

`layer_multiply()`

`layer_normalization()`

`layer_permute()`

`layer_random_brightness()`

`layer_random_contrast()`

`layer_random_crop()`

`layer_random_flip()`

`layer_random_rotation()`

`layer_random_translation()`

`layer_random_zoom()`

`layer_repeat_vector()`

`layer_rescaling()`

`layer_reshape()`

`layer_resizing()`

`layer_rnn()`

`layer_separable_conv_1d()`

`layer_separable_conv_2d()`

`layer_simple_rnn()`

`layer_spatial_dropout_1d()`

`layer_spatial_dropout_2d()`

`layer_spatial_dropout_3d()`

`layer_spectral_normalization()`

`layer_string_lookup()`

`layer_subtract()`

`layer_text_vectorization()`

`layer_tfsm()`

`layer_time_distributed()`

`layer_torch_module_wrapper()`

`layer_unit_normalization()`

`layer_upsampling_1d()`

`layer_upsampling_2d()`

`layer_upsampling_3d()`

`layer_zero_padding_1d()`

`layer_zero_padding_2d()`

`layer_zero_padding_3d()`

`rnn_cell_gru()`

`rnn_cell_lstm()`

`rnn_cell_simple()`

`rnn_cells_stack()`