Have a question? Connect with the community at the TensorFlow Forum Visit Forum


Computes the gradients of 3-D convolution with respect to the input.

input A Tensor. Must be one of the following types: half, float32, float64. Shape [batch, depth, rows, cols, in_channels].
filter A Tensor. Must have the same type as input. Shape [depth, rows, cols, in_channels, out_channels]. in_channels must match between input and filter.
out_backprop A Tensor. Must have the same type as input. Backprop signal of shape [batch, out_depth, out_rows, out_cols, out_channels].
strides A list of ints that has length >= 5. 1-D tensor of length 5. The stride of the sliding window for each dimension of input. Must have strides[0] = strides[4] = 1.
padding A string from: "SAME", "VALID". The type of padding algorithm to use.
dilations An optional list of ints. Defaults to [1, 1, 1, 1, 1].
name A name for the operation (optional).

A Tensor. Has the same type as input.