tf.nn.conv2d_transpose

View source on GitHub

The transpose of conv2d.

tf.nn.conv2d_transpose(
    input, filters, output_shape, strides, padding='SAME',
    data_format='NHWC', dilations=None, name=None
)

This operation is sometimes called "deconvolution" after (Zeiler et al., 2010), but is really the transpose (gradient) of atrous_conv2d rather than an actual deconvolution.

Args
input	A 4-D Tensor of type float and shape [batch, height, width, in_channels] for NHWC data format or [batch, in_channels, height, width] for NCHW data format.
filters	A 4-D Tensor with the same type as input and shape [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, 2 or 4. The stride of the sliding window for each dimension of input. If a single value is given it is replicated in the 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	Either the string"SAME"or"VALID"indicating the type of padding algorithm to use, or a list indicating the explicit paddings at the start and end of each dimension. When explicit padding is used and data_format is"NHWC", this should be in the form[[0, 0], [pad_top, pad_bottom], [pad_left, pad_right], [0, 0]]. When explicit padding used and data_format is"NCHW", this should be in the form[[0, 0], [0, 0], [pad_top, pad_bottom], [pad_left, pad_right]]. </td> </tr><tr> <td>data_format</td> <td> A string. 'NHWC' and 'NCHW' are supported. </td> </tr><tr> <td>dilations</td> <td> An int or list ofintsthat has length1,2or4, defaults to 1. The dilation factor for each dimension ofinput. If a single value is given it is replicated in theHandWdimension. By default theNandCdimensions 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 ofdata_format, see above for details. Dilations in the batch and depth dimensions if a 4-d tensor must be 1. </td> </tr><tr> <td>name`	Optional name for the returned tensor.

Returns
A Tensor with the same type as input.

Raises
ValueError	If input/output depth does not match filter's shape, or if padding is other than 'VALID' or 'SAME'.

References:

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