tf.keras.layers.DepthwiseConv2D

Depthwise 2D convolution.

Inherits From: Conv2D, Layer, Module

tf.keras.layers.DepthwiseConv2D(
    kernel_size, strides=(1, 1), padding='valid', depth_multiplier=1,
    data_format=None, dilation_rate=(1, 1), activation=None, use_bias=True,
    depthwise_initializer='glorot_uniform',
    bias_initializer='zeros', depthwise_regularizer=None,
    bias_regularizer=None, activity_regularizer=None, depthwise_constraint=None,
    bias_constraint=None, **kwargs
)

Depthwise convolution is a type of convolution in which a single convolutional filter is apply to each input channel (i.e. in a depthwise way). You can understand depthwise convolution as being the first step in a depthwise separable convolution.

It is implemented via the following steps:

  • Split the input into individual channels.
  • Convolve each input with the layer's kernel (called a depthwise kernel).
  • Stack the convolved outputs together (along the channels axis).

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

The depth_multiplier argument controls how many output channels are generated per input channel in the depthwise step.

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. 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.
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.
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). 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 An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. Currently, specifying any dilation_rate value != 1 is incompatible with specifying any strides value != 1.
activation Activation function to use. If you don't specify anything, no activation is applied ( see keras.activations).
use_bias Boolean, whether the layer uses a bias vector.
depthwise_initializer Initializer for the depthwise kernel matrix ( see keras.initializers). If None, the default initializer ( 'glorot_uniform') will be used.
bias_initializer Initializer for the bias vector ( see keras.initializers). If None, the default initializer ( 'zeros') will bs used.
depthwise_regularizer Regularizer function applied to the depthwise kernel matrix (see keras.regularizers).
bias_regularizer Regularizer function applied to the bias vector ( see keras.regularizers).
activity_regularizer Regularizer function applied to the output of the layer (its 'activation') ( see keras.regularizers).
depthwise_constraint Constraint function applied to the depthwise kernel matrix ( see keras.constraints).
bias_constraint Constraint function applied to the bias vector ( see keras.constraints).

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'.

Output shape:

4D tensor with shape: [batch_size, channels * depth_multiplier, new_rows, new_cols] if data_format='channels_first' or 4D tensor with shape: [batch_size, new_rows, new_cols, channels * depth_multiplier] if data_format='channels_last'. rows and cols values might have changed due to padding.

A tensor of rank 4 representing activation(depthwiseconv2d(inputs, kernel) + bias).

ValueError if padding is "causal".
ValueError when both strides > 1 and dilation_rate > 1.