Pooling

A primitive to perform max or average pooling. More...

Classes
struct	dnnl::pooling_forward
	Pooling forward propagation primitive. More...
struct	dnnl::pooling_backward
	Pooling backward propagation primitive. More...
struct	dnnl::pooling_v2_forward
	Pooling v2 (dilated pooling) forward propagation primitive. More...
struct	dnnl::pooling_v2_backward
	Pooling v2 (dilated pooling) backward propagation primitive. More...
struct	dnnl_pooling_desc_t
	A descriptor of a pooling operation. More...

Functions
dnnl_status_t DNNL_API	dnnl_pooling_forward_desc_init (dnnl_pooling_desc_t *pool_desc, dnnl_prop_kind_t prop_kind, dnnl_alg_kind_t alg_kind, const dnnl_memory_desc_t *src_desc, const dnnl_memory_desc_t *dst_desc, const dnnl_dims_t strides, const dnnl_dims_t kernel, const dnnl_dims_t padding_l, const dnnl_dims_t padding_r)
	Initializes a descriptor for pooling forward propagation primitive. More...
dnnl_status_t DNNL_API	dnnl_pooling_backward_desc_init (dnnl_pooling_desc_t *pool_desc, dnnl_alg_kind_t alg_kind, const dnnl_memory_desc_t *diff_src_desc, const dnnl_memory_desc_t *diff_dst_desc, const dnnl_dims_t strides, const dnnl_dims_t kernel, const dnnl_dims_t padding_l, const dnnl_dims_t padding_r)
	Initializes a descriptor for pooling backward propagation primitive. More...
dnnl_status_t DNNL_API	dnnl_pooling_v2_forward_desc_init (dnnl_pooling_v2_desc_t *pool_desc, dnnl_prop_kind_t prop_kind, dnnl_alg_kind_t alg_kind, const dnnl_memory_desc_t *src_desc, const dnnl_memory_desc_t *dst_desc, const dnnl_dims_t strides, const dnnl_dims_t kernel, const dnnl_dims_t dilation, const dnnl_dims_t padding_l, const dnnl_dims_t padding_r)
	Initializes a descriptor for pooling v2 (pooling with dilation support) forward propagation primitive. More...
dnnl_status_t DNNL_API	dnnl_pooling_v2_backward_desc_init (dnnl_pooling_v2_desc_t *pool_desc, dnnl_alg_kind_t alg_kind, const dnnl_memory_desc_t *diff_src_desc, const dnnl_memory_desc_t *diff_dst_desc, const dnnl_dims_t strides, const dnnl_dims_t kernel, const dnnl_dims_t dilation, const dnnl_dims_t padding_l, const dnnl_dims_t padding_r)
	Initializes a descriptor for pooling v2 (pooling with dilation support) backward propagation primitive. More...

Detailed Description

A primitive to perform max or average pooling.

Pooling version 2 (dilated pooling).

See also

Pooling in developer guide

A primitive to perform max or average pooling.

See also

Pooling in developer guide

Function Documentation

dnnl_pooling_forward_desc_init()

dnnl_status_t DNNL_API dnnl_pooling_forward_desc_init	(	dnnl_pooling_desc_t *	pool_desc,
		dnnl_prop_kind_t	prop_kind,
		dnnl_alg_kind_t	alg_kind,
		const dnnl_memory_desc_t *	src_desc,
		const dnnl_memory_desc_t *	dst_desc,
		const dnnl_dims_t	strides,
		const dnnl_dims_t	kernel,
		const dnnl_dims_t	padding_l,
		const dnnl_dims_t	padding_r
	)

Initializes a descriptor for pooling forward propagation primitive.

Arrays strides, kernel, padding_l, and padding_r contain values for spatial dimensions only and hence must have the same number of elements as there are spatial dimensions. The order of values is the same as in the tensor: depth (for 3D tensors), height (for 3D and 2D tensors), and width.

Parameters

pool_desc	Output descriptor for a pooling primitive.
prop_kind	Propagation kind. Possible values are dnnl_forward_training and dnnl_forward_inference.
alg_kind	Pooling algorithm kind: either dnnl_pooling_max, dnnl_pooling_avg_include_padding, or dnnl_pooling_avg (same as dnnl_pooling_avg_exclude_padding).
src_desc	Source memory descriptor.
dst_desc	Destination memory descriptor.
strides	Array of strides for spatial dimension.
kernel	Array of kernel spatial dimensions.
padding_l	Array of padding values for low indices for each spatial dimension ([[front,] top,] left).
padding_r	Array of padding values for high indices for each spatial dimension ([[back,] bottom,] right). Can be NULL in which case padding is considered to be symmetrical.

Returns

dnnl_success on success and a status describing the error otherwise.

dnnl_pooling_backward_desc_init()

dnnl_status_t DNNL_API dnnl_pooling_backward_desc_init	(	dnnl_pooling_desc_t *	pool_desc,
		dnnl_alg_kind_t	alg_kind,
		const dnnl_memory_desc_t *	diff_src_desc,
		const dnnl_memory_desc_t *	diff_dst_desc,
		const dnnl_dims_t	strides,
		const dnnl_dims_t	kernel,
		const dnnl_dims_t	padding_l,
		const dnnl_dims_t	padding_r
	)

Initializes a descriptor for pooling backward propagation primitive.

Arrays strides, kernel, padding_l, and padding_r contain values for spatial dimensions only and hence must have the same number of elements as there are spatial dimensions. The order of values is the same as in the tensor: depth (for 3D tensors), height (for 3D and 2D tensors), and width.

Parameters

pool_desc	Output descriptor for a pooling primitive.
alg_kind	Pooling algorithm kind: either dnnl_pooling_max, dnnl_pooling_avg_include_padding, or dnnl_pooling_avg (same as dnnl_pooling_avg_exclude_padding).
diff_src_desc	Diff source memory descriptor.
diff_dst_desc	Diff destination memory descriptor.
strides	Array of strides for spatial dimension.
kernel	Array of kernel spatial dimensions.
padding_l	Array of padding values for low indices for each spatial dimension ([[front,] top,] left).
padding_r	Array of padding values for high indices for each spatial dimension ([[back,] bottom,] right). Can be NULL in which case padding is considered to be symmetrical.

Returns

dnnl_success on success and a status describing the error otherwise.

dnnl_pooling_v2_forward_desc_init()

dnnl_status_t DNNL_API dnnl_pooling_v2_forward_desc_init	(	dnnl_pooling_v2_desc_t *	pool_desc,
		dnnl_prop_kind_t	prop_kind,
		dnnl_alg_kind_t	alg_kind,
		const dnnl_memory_desc_t *	src_desc,
		const dnnl_memory_desc_t *	dst_desc,
		const dnnl_dims_t	strides,
		const dnnl_dims_t	kernel,
		const dnnl_dims_t	dilation,
		const dnnl_dims_t	padding_l,
		const dnnl_dims_t	padding_r
	)

Initializes a descriptor for pooling v2 (pooling with dilation support) forward propagation primitive.

Arrays strides, kernel, dilation, padding_l and padding_r contain values for spatial dimensions only and hence must have the same number of elements as there are spatial dimensions. The order of values is the same as in the tensor: depth (for 3D tensors), height (for 3D and 2D tensors), and width.

Parameters

pool_desc	Output descriptor for a pooling primitive.
prop_kind	Propagation kind. Possible values are dnnl_forward_training and dnnl_forward_inference.
alg_kind	Pooling algorithm kind: either dnnl_pooling_max, dnnl_pooling_avg_include_padding, or dnnl_pooling_avg (same as dnnl_pooling_avg_exclude_padding).
src_desc	Source memory descriptor.
dst_desc	Destination memory descriptor.
strides	Array of strides for spatial dimension.
kernel	Array of kernel spatial dimensions.
dilation	Array of dilations for spatial dimension.
padding_l	Array of padding values for low indices for each spatial dimension ([[front,] top,] left).
padding_r	Array of padding values for high indices for each spatial dimension ([[back,] bottom,] right). Can be NULL in which case padding is considered to be symmetrical.

Returns

dnnl_success on success and a status describing the error otherwise.

Examples:

cnn_inference_f32.c, and cpu_cnn_training_f32.c.

dnnl_pooling_v2_backward_desc_init()

dnnl_status_t DNNL_API dnnl_pooling_v2_backward_desc_init	(	dnnl_pooling_v2_desc_t *	pool_desc,
		dnnl_alg_kind_t	alg_kind,
		const dnnl_memory_desc_t *	diff_src_desc,
		const dnnl_memory_desc_t *	diff_dst_desc,
		const dnnl_dims_t	strides,
		const dnnl_dims_t	kernel,
		const dnnl_dims_t	dilation,
		const dnnl_dims_t	padding_l,
		const dnnl_dims_t	padding_r
	)

Initializes a descriptor for pooling v2 (pooling with dilation support) backward propagation primitive.

Arrays strides, kernel, dilation, padding_l and padding_r contain values for spatial dimensions only and hence must have the same number of elements as there are spatial dimensions. The order of values is the same as in the tensor: depth (for 3D tensors), height (for 3D and 2D tensors), and width.

Parameters

pool_desc	Output descriptor for a pooling primitive.
alg_kind	Pooling algorithm kind: either dnnl_pooling_max, dnnl_pooling_avg_include_padding, or dnnl_pooling_avg (same as dnnl_pooling_avg_exclude_padding).
diff_src_desc	Diff source memory descriptor.
diff_dst_desc	Diff destination memory descriptor.
strides	Array of strides for spatial dimension.
kernel	Array of kernel spatial dimensions.
dilation	Array of dilations for spatial dimension.
padding_l	Array of padding values for low indices for each spatial dimension ([[front,] top,] left).
padding_r	Array of padding values for high indices for each spatial dimension ([[back,] bottom,] right). Can be NULL in which case padding is considered to be symmetrical.

Returns

dnnl_success on success and a status describing the error otherwise.

Examples:

cpu_cnn_training_f32.c.