Pooling Functions

Perform max and average pooling operations

Machine-readable model

• arm_max_pool_f32functionMax pooling.
• arm_avg_pool_f32functionAverage pooling.
• arm_max_pool_f16functionMax pooling.
• arm_avg_pool_f16functionAverage pooling.

function

arm_max_pool_f32

C

Max pooling.

Include/arm_nnfunctions_flt.h:540

arm_cmsis_nn_status arm_max_pool_f32(
    const cmsis_nn_context *ctx,
    const cmsis_nn_pool_params_f32 *pool_params,
    const cmsis_nn_dims *input_dims,
    const float32_t *src,
    const cmsis_nn_dims *filter_dims,
    const cmsis_nn_dims *output_dims,
    float32_t *dst
)

Max pooling.

Parameters

Parameters of arm_max_pool_f32

Name	Type	Direction	Description
ctx	const cmsis_nn_context *	in, out	Function context that may hold a temporary scratch buffer.
pool_params	const cmsis_nn_pool_params_f32 *	in	Pooling parameters (stride, padding and activation clamp).
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions.
src	const float32_t *	in	Pointer to the input tensor data.
filter_dims	const cmsis_nn_dims *	in	Pooling kernel dimensions.
output_dims	const cmsis_nn_dims *	in	Output tensor dimensions.
dst	float32_t *	out	Pointer to the output tensor data.

Returns

Returns of arm_max_pool_f32

Description

`ARM_CMSIS_NN_SUCCESS` on success, including an output with no rows or no columns (an extent of 0 or less), which writes nothing; `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments: a NULL pointer argument other than ctx, a batch count below 1, a pooling window that does not overlap the input, or window positions (output index * stride - padding, including one stride past the last window, plus the filter extent, and input size minus position) that do not fit in an int32_t. Nothing is written to dst then.

function

arm_avg_pool_f32

C

Average pooling.

Include/arm_nnfunctions_flt.h:565

arm_cmsis_nn_status arm_avg_pool_f32(
    const cmsis_nn_context *ctx,
    const cmsis_nn_pool_params_f32 *pool_params,
    const cmsis_nn_dims *input_dims,
    const float32_t *src,
    const cmsis_nn_dims *filter_dims,
    const cmsis_nn_dims *output_dims,
    float32_t *dst
)

Average pooling.

Parameters

Parameters of arm_avg_pool_f32

Name	Type	Direction	Description
ctx	const cmsis_nn_context *	in, out	Function context that may hold a temporary scratch buffer.
pool_params	const cmsis_nn_pool_params_f32 *	in	Pooling parameters (stride, padding and activation clamp).
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions.
src	const float32_t *	in	Pointer to the input tensor data.
filter_dims	const cmsis_nn_dims *	in	Pooling kernel dimensions.
output_dims	const cmsis_nn_dims *	in	Output tensor dimensions.
dst	float32_t *	out	Pointer to the output tensor data.

Returns

Returns of arm_avg_pool_f32

Description

`ARM_CMSIS_NN_SUCCESS` on success, including an output with no rows or no columns (an extent of 0 or less), which writes nothing; `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments: a NULL pointer argument other than ctx, a batch count below 1, a pooling window that does not overlap the input, or window positions (output index * stride - padding, including one stride past the last window, plus the filter extent, and input size minus position) that do not fit in an int32_t. Nothing is written to dst then.

function

arm_max_pool_f16

C

Max pooling.

Include/arm_nnfunctions_flt.h:2695

arm_cmsis_nn_status arm_max_pool_f16(
    const cmsis_nn_context *ctx,
    const cmsis_nn_pool_params_f16 *pool_params,
    const cmsis_nn_dims *input_dims,
    const float16_t *src,
    const cmsis_nn_dims *filter_dims,
    const cmsis_nn_dims *output_dims,
    float16_t *dst
)

Max pooling.

Note

The output activation clamp on the scalar (non-MVE) build path is the bit-classified clamp of #380, so a NaN that reaches the clamp comes back as NaN at every optimization level on the gated toolchains rather than as a bound. A NaN rarely reaches it, though: the scalar max reduction uses an ordered compare that drops a NaN window element (and its NaN behavior at the shipped -Ofast is unspecified), and the MVE path’s vmaxnmq reduction and vmaxnmq/vminnmq clamp suppress NaN, so this kernel does not promise NaN propagation end to end.

Parameters

Parameters of arm_max_pool_f16

Name	Type	Direction	Description
ctx	const cmsis_nn_context *	in, out	Function context that may hold a temporary scratch buffer.
pool_params	const cmsis_nn_pool_params_f16 *	in	Pooling parameters (stride, padding and activation clamp).
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions.
src	const float16_t *	in	Pointer to the input tensor data.
filter_dims	const cmsis_nn_dims *	in	Pooling kernel dimensions.
output_dims	const cmsis_nn_dims *	in	Output tensor dimensions.
dst	float16_t *	out	Pointer to the output tensor data.

Returns

Returns of arm_max_pool_f16

Description

`ARM_CMSIS_NN_SUCCESS` on success, including an output with no rows or no columns (an extent of 0 or less), which writes nothing; `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments: a NULL pointer argument other than ctx, a batch count below 1, a pooling window that does not overlap the input, or window positions (output index * stride - padding, including one stride past the last window, plus the filter extent, and input size minus position) that do not fit in an int32_t. Nothing is written to dst then.

function

arm_avg_pool_f16

C

Average pooling.

Include/arm_nnfunctions_flt.h:2712

arm_cmsis_nn_status arm_avg_pool_f16(
    const cmsis_nn_context *ctx,
    const cmsis_nn_pool_params_f16 *pool_params,
    const cmsis_nn_dims *input_dims,
    const float16_t *src,
    const cmsis_nn_dims *filter_dims,
    const cmsis_nn_dims *output_dims,
    float16_t *dst
)

Average pooling.

Note

On non-MVE builds every output element goes through the bit-classified scalar clamp of #380, so a NaN in the pooling window propagates through the window sum and the output activation clamp to the output element at every optimization level on the gated toolchains, including the shipped -Ofast. On MVE builds the clamp is vmaxnmq/vminnmq with no NaN restore, so a NaN resolves to a clamp bound there instead.

Parameters

Parameters of arm_avg_pool_f16

Name	Type	Direction	Description
ctx	const cmsis_nn_context *	in, out	Function context that may hold a temporary scratch buffer.
pool_params	const cmsis_nn_pool_params_f16 *	in	Pooling parameters (stride, padding and activation clamp).
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions.
src	const float16_t *	in	Pointer to the input tensor data.
filter_dims	const cmsis_nn_dims *	in	Pooling kernel dimensions.
output_dims	const cmsis_nn_dims *	in	Output tensor dimensions.
dst	float16_t *	out	Pointer to the output tensor data.

Returns

Returns of arm_avg_pool_f16

Description

`ARM_CMSIS_NN_SUCCESS` on success, including an output with no rows or no columns (an extent of 0 or less), which writes nothing; `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments: a NULL pointer argument other than ctx, a batch count below 1, a pooling window that does not overlap the input, or window positions (output index * stride - padding, including one stride past the last window, plus the filter extent, and input size minus position) that do not fit in an int32_t. Nothing is written to dst then.