A primitive to perform max or average pooling. 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 pooling descriptor `pool_desc` for forward propagation using `prop_kind` (possible values are dnnl_forward_training and dnnl_forward_inference), `alg_kind`, memory descriptors, and pooling parameters in the spatial domain: `strides`, `kernel` sizes, `padding_l`, and `padding_r`. 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 pooling descriptor `pool_desc` for backward propagation using `alg_kind`, memory descriptors, and pooling parameters in the spatial domain: `strides`, `kernel` sizes, `padding_l`, and `padding_r`. More...

Detailed Description

A primitive to perform max or average pooling.

See also: Pooling in developer guide; Pooling in C++ API

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 pooling descriptor pool_desc for forward propagation using prop_kind (possible values are dnnl_forward_training and dnnl_forward_inference), alg_kind, memory descriptors, and pooling parameters in the spatial domain: strides, kernel sizes, padding_l, and padding_r.

Note: If padding_r is NULL, the padding is supposed to be symmetric.

Inputs:

src (dnnl_query_src_md, 0)

Outputs:

dst (dnnl_query_dst_md, 0)
workspace (dnnl_query_workspace_md, 0), if alg_kind = dnnl_pooling_max and prop_kind = dnnl_forward_training

Examples:: cnn_inference_f32.c, and cpu_cnn_training_f32.c.

◆ 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 pooling descriptor pool_desc for backward propagation using alg_kind, memory descriptors, and pooling parameters in the spatial domain: strides, kernel sizes, padding_l, and padding_r.

Note: If padding_r is NULL, the padding is supposed to be symmetric.