tf.nn.conv3d_transpose(
value,
filter,
output_shape,
strides,
padding='SAME',
data_format='NDHWC',
name=None
)
Defined in tensorflow/python/ops/nn_ops.py
.
The transpose of conv3d
.
This operation is sometimes called "deconvolution" after Deconvolutional
Networks, but is
actually the transpose (gradient) of conv3d
rather than an actual
deconvolution.
Args:
value
: A 5-DTensor
of typefloat
and shape[batch, depth, height, width, in_channels]
.filter
: A 5-DTensor
with the same type asvalue
and shape[depth, height, width, output_channels, in_channels]
.filter
'sin_channels
dimension must match that ofvalue
.output_shape
: A 1-DTensor
representing the output shape of the deconvolution op.strides
: A list of ints. The stride of the sliding window for each dimension of the input tensor.padding
: A string, either'VALID'
or'SAME'
. The padding algorithm. See the "returns" section oftf.nn.convolution
for details.data_format
: A string, either'NDHWC'
or'NCDHW
' specifying the layout of the input and output tensors. Defaults to'NDHWC'
.name
: Optional name for the returned tensor.
Returns:
A Tensor
with the same type as value
.
Raises:
ValueError
: If input/output depth does not matchfilter
's shape, or if padding is other than'VALID'
or'SAME'
.