# tensorflow::ops::FractionalAvgPool::Attrs `#include ` Optional attribute setters for [FractionalAvgPool](https://www.tensorflow.org/versions/r2.12/api_docs/cc/class/tensorflow/ops/fractional-avg-pool#classtensorflow_1_1ops_1_1_fractional_avg_pool). ## Summary | ### Public attributes || |---|---| | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1a61f280a9ce83539a26b89a4651db132c = false` | `bool` | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1a50e61bdb802b360a726be83b8660daad = false` | `bool` | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1afac27e665631052f0b4f64af3ceefcfe = false` | `bool` | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1a9faa5b56888e5aa067e9cc4e4ea0ff3a = 0` | `int64` | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1adda88abb2a9de85ca5971ef4315d9bb6 = 0` | `int64` | | ### Public functions || |---|---| | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1a873dc80042303bc7f645e56ebb80f7aa(bool x)` | `TF_MUST_USE_RESULT https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs` When set to True, a fixed pooling region will be used when iterating over a [FractionalAvgPool](https://www.tensorflow.org/versions/r2.12/api_docs/cc/class/tensorflow/ops/fractional-avg-pool#classtensorflow_1_1ops_1_1_fractional_avg_pool) node in the computation graph. | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1a4e52f1f09ad181656cef01b39205ed6e(bool x)` | `TF_MUST_USE_RESULT https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs` When set to True, it means when pooling, the values at the boundary of adjacent pooling cells are used by both cells. | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1ac235854793b77d8528a50eb19c7d3009(bool x)` | `TF_MUST_USE_RESULT https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs` When set to True, generates the pooling sequence in a pseudorandom fashion, otherwise, in a random fashion. | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1a44e0ebd8a59b50d13a18fcce75087c8c(int64 x)` | `TF_MUST_USE_RESULT https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs` If either seed or seed2 are set to be non-zero, the random number generator is seeded by the given seed. | | `https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs_1afc60d67272d3e8eea9e3da45b6b17d12(int64 x)` | `TF_MUST_USE_RESULT https://www.tensorflow.org/versions/r2.12/api_docs/cc/struct/tensorflow/ops/fractional-avg-pool/attrs#structtensorflow_1_1ops_1_1_fractional_avg_pool_1_1_attrs` An second seed to avoid seed collision. | ## Public attributes ### deterministic_ ``` bool tensorflow::ops::FractionalAvgPool::Attrs::deterministic_ = false ``` ### overlapping_ ``` bool tensorflow::ops::FractionalAvgPool::Attrs::overlapping_ = false ``` ### pseudo_random_ ``` bool tensorflow::ops::FractionalAvgPool::Attrs::pseudo_random_ = false ``` ### seed2_ ``` int64 tensorflow::ops::FractionalAvgPool::Attrs::seed2_ = 0 ``` ### seed_ ``` int64 tensorflow::ops::FractionalAvgPool::Attrs::seed_ = 0 ``` ## Public functions ### Deterministic ``` TF_MUST_USE_RESULT Attrs tensorflow::ops::FractionalAvgPool::Attrs::Deterministic( bool x ) ``` When set to True, a fixed pooling region will be used when iterating over a [FractionalAvgPool](https://www.tensorflow.org/versions/r2.12/api_docs/cc/class/tensorflow/ops/fractional-avg-pool#classtensorflow_1_1ops_1_1_fractional_avg_pool) node in the computation graph. Mainly used in unit test to make [FractionalAvgPool](https://www.tensorflow.org/versions/r2.12/api_docs/cc/class/tensorflow/ops/fractional-avg-pool#classtensorflow_1_1ops_1_1_fractional_avg_pool) deterministic. Defaults to false ### Overlapping ``` TF_MUST_USE_RESULT Attrs tensorflow::ops::FractionalAvgPool::Attrs::Overlapping( bool x ) ``` When set to True, it means when pooling, the values at the boundary of adjacent pooling cells are used by both cells. For example: `index 0 1 2 3 4` `value 20 5 16 3 7` If the pooling sequence is \[0, 2, 4\], then 16, at index 2 will be used twice. The result would be \[41/3, 26/3\] for fractional avg pooling. Defaults to false ### PseudoRandom ``` TF_MUST_USE_RESULT Attrs tensorflow::ops::FractionalAvgPool::Attrs::PseudoRandom( bool x ) ``` When set to True, generates the pooling sequence in a pseudorandom fashion, otherwise, in a random fashion. Check paper [Benjamin Graham, Fractional Max-Pooling](http://arxiv.org/abs/1412.6071) for difference between pseudorandom and random. Defaults to false ### Seed ``` TF_MUST_USE_RESULT Attrs tensorflow::ops::FractionalAvgPool::Attrs::Seed( int64 x ) ``` If either seed or seed2 are set to be non-zero, the random number generator is seeded by the given seed. Otherwise, it is seeded by a random seed. Defaults to 0 ### Seed2 ``` TF_MUST_USE_RESULT Attrs tensorflow::ops::FractionalAvgPool::Attrs::Seed2( int64 x ) ``` An second seed to avoid seed collision. Defaults to 0