2D convolution with separable filters.
View aliases
Compat aliases for migration
See Migration guide for more details.
tf.keras.backend.separable_conv2d(
x, depthwise_kernel, pointwise_kernel, strides=(1, 1), padding='valid',
data_format=None, dilation_rate=(1, 1)
)
Arguments | |
---|---|
x
|
input tensor |
depthwise_
|
convolution kernel for the depthwise convolution. |
pointwise_
|
kernel for the 1x1 convolution. |
strides
|
strides tuple (length 2). |
padding
|
string, "same" or "valid" .
|
data_
|
string, "channels_ or "channels_ .
|
dilation_
|
tuple of integers, dilation rates for the separable convolution. |
Returns | |
---|---|
Output tensor. |
Raises | |
---|---|
ValueError
|
if data_ is neither channels_ or
channels_ .
|
ValueError
|
if strides is not a tuple of 2 integers.
|