2D convolution with separable filters.
2D convolution with separable filters.
k_separable_conv2d( x, depthwise_kernel, pointwise_kernel, strides = c(1, 1), padding = "valid", data_format = NULL, dilation_rate = c(1, 1) )
x |
input tensor |
depthwise_kernel |
convolution kernel for the depthwise convolution. |
pointwise_kernel |
kernel for the 1x1 convolution. |
strides |
strides list (length 2). |
padding |
string, |
data_format |
string, |
dilation_rate |
list of integers, dilation rates for the separable convolution. |
Output tensor.
This function is part of a set of Keras backend functions that enable lower level access to the core operations of the backend tensor engine (e.g. TensorFlow, CNTK, Theano, etc.).
You can see a list of all available backend functions here: https://keras.rstudio.com/articles/backend.html#backend-functions.
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.