tf.nn.atrous_conv2d_transpose( value, filters, output_shape, rate, padding, name=None )
Defined in tensorflow/python/ops/nn_ops.py
.
See the guide: Neural Network > Convolution
The transpose of atrous_conv2d
.
This operation is sometimes called "deconvolution" after Deconvolutional Networks, but is actually the transpose (gradient) of atrous_conv2d
rather than an actual deconvolution.
value
: A 4-D Tensor
of type float
. It needs to be in the default NHWC
format. Its shape is [batch, in_height, in_width, in_channels]
.filters
: A 4-D Tensor
with the same type as value
and shape [filter_height, filter_width, out_channels, in_channels]
. filters
' in_channels
dimension must match that of value
. Atrous convolution is equivalent to standard convolution with upsampled filters with effective height filter_height + (filter_height - 1) * (rate - 1)
and effective width filter_width + (filter_width - 1) * (rate - 1)
, produced by inserting rate - 1
zeros along consecutive elements across the filters
' spatial dimensions.output_shape
: A 1-D Tensor
of shape representing the output shape of the deconvolution op.rate
: A positive int32. The stride with which we sample input values across the height
and width
dimensions. Equivalently, the rate by which we upsample the filter values by inserting zeros across the height
and width
dimensions. In the literature, the same parameter is sometimes called input stride
or dilation
.padding
: A string, either 'VALID'
or 'SAME'
. The padding algorithm.name
: Optional name for the returned tensor.A Tensor
with the same type as value
.
ValueError
: If input/output depth does not match filters
' shape, or if padding is other than 'VALID'
or 'SAME'
, or if the rate
is less than one, or if the output_shape is not a tensor with 4 elements.
© 2018 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/api_docs/python/tf/nn/atrous_conv2d_transpose