#include <nn_ops.h>
Optional attribute setters for QuantizedConv2D.
| Public attributes | |
|---|---|
dilations_ = {1, 1, 1, 1} | gtl::ArraySlice< int > |
out_type_ = DT_QINT32 | DataType |
| Public functions | |
|---|---|
Dilations(const gtl::ArraySlice< int > & x) | TF_MUST_USE_RESULT Attrs 1-D tensor of length 4. |
OutType(DataType x) | TF_MUST_USE_RESULT Attrs Defaults to DT_QINT32. |
gtl::ArraySlice< int > tensorflow::ops::QuantizedConv2D::Attrs::dilations_ = {1, 1, 1, 1} DataType tensorflow::ops::QuantizedConv2D::Attrs::out_type_ = DT_QINT32
TF_MUST_USE_RESULT Attrs tensorflow::ops::QuantizedConv2D::Attrs::Dilations( const gtl::ArraySlice< int > & x )
1-D tensor of length 4.
The dilation factor for each dimension of input. 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 must be 1.
Defaults to [1, 1, 1, 1]
TF_MUST_USE_RESULT Attrs tensorflow::ops::QuantizedConv2D::Attrs::OutType( DataType x )
Defaults to DT_QINT32.
© 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/cc/struct/tensorflow/ops/quantized-conv2-d/attrs.html