tfp.experimental.nn.util.make_convolution_transpose_fn_with_subkernels

Like tf.nn.conv2d except applies batch of kernels to batch of x.

tfp.experimental.nn.util.make_convolution_transpose_fn_with_subkernels(
    filter_shape,
    strides,
    padding,
    rank=2,
    dilations=None,
    dtype=tf.int32,
    validate_args=False,
    name=None
)