Like tf.nn.conv2d except applies batch of kernels to batch of x.
tfp.experimental.nn.util.make_convolution_transpose_fn_with_dilation(
filter_shape,
strides,
padding,
rank=2,
dilations=None,
dtype=tf.int32,
validate_args=False,
name=None
)
This version tends to be fastest on GPU. It implements the transposed
convolution as a regular convolution of an image that is dilated by
interleaving rows and columns of zeros equal to the number of strides.
Args |
|---|
filter_shape
|
...
|
strides
|
...
|
padding
|
...
|
rank
|
...
|
dilations
|
...
|
dtype
|
...
|
validate_args
|
...
|
name
|
...
|
Returns |
|---|
convolution_transpose_fn
|
A callable that takes an input Tensor and kernel
and applies the transpose convolution operation.
|
View source on GitHub