Intel® oneAPI Deep Neural Network Library Developer Guide and Reference

Developer Guide and Reference

  • 2022.1
  • 04/11/2022
  • Public Content
Contents

struct dnnl::batch_normalization_backward::desc

Overview

Descriptor for a batch normalization backward propagation primitive. More…
#include <dnnl.hpp>

struct desc
{
    // fields

    dnnl_batch_normalization_desc_t data;

    // construction

    desc(
        prop_kind aprop_kind,
        const memory::desc& diff_data_desc,
        const memory::desc& data_desc,
        float epsilon,
        normalization_flags flags
        );
};

Detailed Documentation

Descriptor for a batch normalization backward propagation primitive.
Construction
desc(
    prop_kind aprop_kind,
    const memory::desc& diff_data_desc,
    const memory::desc& data_desc,
    float epsilon,
    normalization_flags flags
    )
Constructs a batch normalization descriptor for backward propagation.
Parameters:
aprop_kind
Propagation kind. Possible values are dnnl::prop_kind::backward_data and dnnl::prop_kind::backward (diffs for all parameters are computed in this case).
diff_data_desc
Diff source and diff destination memory descriptor.
data_desc
Source memory descriptor.
epsilon
Batch normalization epsilon parameter.
flags
Batch normalization flags (dnnl::normalization_flags).

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.