Deep Neural Network Library (DNNL)  1.3.0
Performance library for Deep Learning
Batch Normalization

API Reference

The batch normalization primitive performs a forward or backward batch normalization operation on 0D, 2D, or 3D spatial data.

The batch normalization operation is defined by the following formulas. We show formulas only for 2D spatial data which are straightforward to generalize to cases of higher and lower dimensions. Variable names follow the standard Naming Conventions.

Forward

\[ \dst(n, c, h, w) = \gamma(c) \cdot \frac{\src(n, c, h, w) - \mu(c)} {\sqrt{\sigma^2(c) + \varepsilon}} + \beta(c), \]

where

Mean and variance are computed at runtime or provided by a user. When mean and variance are computed at runtime, the following formulas are used:

The \(\gamma(c)\) and \(\beta(c)\) tensors are considered learnable.

In training mode, the primitive also optionally supports fusion with ReLU activation with zero negative slope applied to the result (see dnnl_fuse_norm_relu flag).

Note
  • The batch normalization primitive computes population mean and variance and not the sample or unbiased versions that are typically used to compute running mean and variance.
  • Using the mean and variance computed by the batch normalization primitive, running mean and variance \(\hat\mu\) and \(\hat\sigma^2\) can be computed as

    \[ \hat\mu := \alpha \cdot \hat\mu + (1 - \alpha) \cdot \mu, \\ \hat\sigma^2 := \alpha \cdot \hat\sigma^2 + (1 - \alpha) \cdot \sigma^2. \]

Difference Between Forward Training and Forward Inference

Backward

The backward propagation computes \(\diffsrc(n, c, h, w)\), \(\diffgamma(c)^*\), and \(\diffbeta(c)^*\) based on \(\diffdst(n, c, h, w)\), \(\src(n, c, h, w)\), \(\mu(c)\), \(\sigma^2(c)\), \(\gamma(c) ^*\), and \(\beta(c) ^*\).

The tensors marked with an asterisk are used only when the primitive is configured to use \(\gamma(c)\) and \(\beta(c)\) (i.e., dnnl_use_scaleshift is set).

Execution Arguments

Depending on the flags and propagation kind, the batch normalization primitive requires different inputs and outputs. For clarity, a summary is shown below.

dnnl_forward_inference dnnl_forward_training dnnl_backward dnnl_backward_data
(none) Inputs: \(\src\)

Outputs: \(\dst\)
Inputs: \(\src\)

Outputs: \(\dst\), \(\mu\), \(\sigma^2\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\)

Outputs: \(\diffsrc\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\)

Outputs: \(\diffsrc\)
dnnl_use_global_stats Inputs: \(\src\), \(\mu\), \(\sigma^2\)

Outputs: \(\dst\)
Inputs: \(\src\), \(\mu\), \(\sigma^2\)

Outputs: \(\dst\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\)

Outputs: \(\diffsrc\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\)

Outputs: \(\diffsrc\)
dnnl_use_scaleshift Inputs: \(\src\), \(\gamma\), \(\beta\)

Outputs: \(\dst\)
Inputs: \(\src\), \(\gamma\), \(\beta\)

Outputs: \(\dst\), \(\mu\), \(\sigma^2\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\), \(\gamma\), \(\beta\)

Outputs: \(\diffsrc\), \(\diffgamma\), \(\diffbeta\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\), \(\gamma\), \(\beta\)

Outputs: \(\diffsrc\)
dnnl_use_global_stats | dnnl_use_scaleshift Inputs: \(\src\), \(\mu\), \(\sigma^2\), \(\gamma\), \(\beta\)

Outputs: \(\dst\)
Inputs: \(\src\), \(\mu\), \(\sigma^2\), \(\gamma\), \(\beta\)

Outputs: \(\dst\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\), \(\gamma\), \(\beta\)

Outputs: \(\diffsrc\), \(\diffgamma\), \(\diffbeta\)
Inputs: \(\diffdst\), \(\src\), \(\mu\), \(\sigma^2\), \(\gamma\), \(\beta\)

Outputs: \(\diffsrc\)
flags | dnnl_fuse_norm_relu Inputs: same as with flags

Outputs: same as with flags
Inputs: same as with flags

Outputs: same as with flags, Workspace
Inputs: same as with flags, Workspace

Outputs: same as with flags
Inputs: same as with flags, Workspace

Outputs: same as with flags

When executed, the inputs and outputs should be mapped to an execution argument index as specified by the following table.

Primitive input/output Execution argument index
\(\src\) DNNL_ARG_SRC
\(\gamma, \beta\) DNNL_ARG_SCALE_SHIFT
mean ( \(\mu\)) DNNL_ARG_MEAN
variance ( \(\sigma\)) DNNL_ARG_VARIANCE
\(\dst\) DNNL_ARG_DST
workspace DNNL_ARG_WORKSPACE
\(\diffdst\) DNNL_ARG_DIFF_DST
\(\diffsrc\) DNNL_ARG_DIFF_SRC
\(\diffgamma, \diffbeta\) DNNL_ARG_DIFF_SCALE_SHIFT

Implementation Details

General Notes

  1. The different flavors of the primitive are partially controlled by the flags parameter that is passed to the operation descriptor initialization function (e.g., dnnl::batch_normalization_forward::desc::desc()). Multiple flags can be set using the bitwise OR operator (|).
  2. For forward propagation, the mean and variance might be either computed at runtime (in which case they are outputs of the primitive) or provided by a user (in which case they are inputs). In the latter case, a user must set the dnnl_use_global_stats flag. For the backward propagation, the mean and variance are always input parameters.
  3. The memory format and data type for src and dst are assumed to be the same, and in the API they are typically referred to as data (e.g., see data_desc in dnnl::batch_normalization_forward::desc::desc()). The same is true for diff_src and diff_dst. The corresponding memory descriptors are referred to as diff_data_desc.
  4. Both forward and backward propagation support in-place operations, meaning that src can be used as input and output for forward propagation, and diff_dst can be used as input and output for backward propagation. In case of an in-place operation, the original data will be overwritten.
  5. As mentioned above, the batch normalization primitive can be fused with ReLU activation even in the training mode. In this case, on the forward propagation the primitive has one additional output, workspace, that should be passed during the backward propagation.

Data Type Support

The operation supports the following combinations of data types:

Propagation Source / Destination Mea
forward / backward f32, bf16 f32
forward f16 f32
forward s8 f32
Warning
There might be hardware- or implementation-specific restrictions. Check the Implementation Limitations section below.

Data Representation

Mean and Variance

The mean ( \(\mu\)) and variance ( \(\sigma^2\)) are separate 1D tensors of size \(C\).

The format of the corresponding memory object must be dnnl_x (dnnl_a).

Scale and Shift

If used, the scale ( \(\gamma\)) and shift ( \(\beta\)) are combined in a single 2D tensor of shape \(2 \times C\).

The format of the corresponding memory object must be dnnl_nc (dnnl_ab).

Source, Destination, and Their Gradients

Like other CNN primitives, the batch normalization primitive expects data to be \(N \times C \times SP_n \times \cdots \times SP_0\) tensor.

The batch normalization primitive is optimized for the following memory formats:

Spatial Logical tensor Imp
0D NC dnnl_nc (dnnl_ab)
2D NCHW dnnl_nchw (dnnl_abcd), dnnl_nhwc (dnnl_acdb), optimized^
3D NCDHW dnnl_ncdhw (dnnl_abcde), dnnl_ndhwc (dnnl_acdeb), optimized^

Here optimized^ means the format that comes out of any preceding compute-intensive primitive.

Post-ops and Attributes

Post-ops and attributes enable you to modify the behavior of the batch normalization primitive by chaining certain operations after the batch normalization operation. The following post-ops are supported by batch normalization primitives:

Propagation Type Operation Des
forward post-op eltwise Applies an Eltwise operation to the result (currently only dnnl_eltwise_relu algorithm is supported)
Note
As mentioned in Primitive Attributes, the post-ops should be used for inference only. For instance, using ReLU as a post-op would not produce the additional output workspace that is required to compute backward propagation correctly. Hence, in case of training one should use the dnnl_fuse_norm_relu directly.

Implementation Limitations

  1. Refer to Data Types for limitations related to data types support.
  2. For the data types that have forward propagation support only, mean and variance must be provided by a user (i.e., dnnl_use_global_stats is set).

Performance Tips

  1. For backward propagation, use the same memory format for src, diff_dst, and diff_src (the format of the diff_dst and diff_src are always the same because of the API). Different formats are functionally supported but lead to highly suboptimal performance.
  2. Use in-place operations whenever possible.