tf.nn.conv3d_transpose

The transpose of conv3d.

This operation is sometimes called "deconvolution" after (Zeiler et al., 2010), but is really the transpose (gradient) of conv3d rather than an actual deconvolution.

Args
input A 5-D Tensor of type float and shape [batch, depth, height, width, in_channels] for NDHWC data format or [batch, in_channels, depth, height, width] for NCDHW data format.
filters A 5-D Tensor with the same type as input and shape [depth, height, width, output_channels, in_channels]. filter's in_channels dimension must match that of input.
output_shape A 1-D Tensor representing the output shape of the deconvolution op.
strides An int or list of ints that has length 1, 3 or 5. The stride of the sliding window for each dimension of input. If a single value is given it is replicated in the D, H and W dimension. By default the N and C dimensions are set to 0. The dimension order is determined by the value of data_format, see below for details.
padding A string, either 'VALID' or 'SAME'. The padding algorithm. See the "returns" section of tf.nn.convolution for details.
data_format A string. 'NDHWC' and 'NCDHW' are supported.
dilations An int or list of ints that has length 1, 3 or 5, defaults to 1. The dilation factor for each dimension ofinput. If a single value is given it is replicated in the D, H and W dimension. By default the N and C dimensions are set to 1. If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of data_format, see above for details. Dilations in the batch and depth dimensions if a 5-d tensor must be 1.
name Optional name for the returned tensor.
Returns
A Tensor with the same type as input.

References:

Deconvolutional Networks: Zeiler et al., 2010 (pdf)

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.4/api_docs/python/tf/nn/conv3d_transpose