NNSupport

Machine-readable model

• arm_transpose_f32functionTranspose a floating-point tensor.
• arm_concatenation_f32_xfunctionConcatenate tensors along the X axis.
• arm_concatenation_f32_yfunctionConcatenate tensors along the Y axis.
• arm_concatenation_f32_zfunctionConcatenate tensors along the Z axis.
• arm_concatenation_f32_wfunctionConcatenate tensors along the W axis.
• arm_concatenation_f32functionConcatenate float32 tensors of any rank along one axis.
• arm_split_f32functionSplit a float32 tensor of any rank into several tensors along one axis.
• arm_pack_f32functionStack float32 tensors of equal shape along a new axis (TFLite PACK).
• arm_unpack_f32functionUnstack a float32 tensor along one axis into inputshape[axis] tensors (TFLite UNPACK).
• arm_batch_norm_f32functionApply batch normalization.
• arm_reshape_f32functionReshape by copying data without changing element order.
• arm_transpose_f16functionTranspose a floating-point tensor.
• arm_concatenation_f16_xfunctionConcatenate tensors along the X axis.
• arm_concatenation_f16_yfunctionConcatenate tensors along the Y axis.
• arm_concatenation_f16_zfunctionConcatenate tensors along the Z axis.
• arm_concatenation_f16_wfunctionConcatenate tensors along the W axis.
• arm_concatenation_f16functionConcatenate float32 tensors of any rank along one axis.
• arm_pack_f16functionStack float32 tensors of equal shape along a new axis (TFLite PACK).
• arm_unpack_f16functionUnstack a float32 tensor along one axis into inputshape[axis] tensors (TFLite UNPACK).
• arm_batch_norm_f16functionApply batch normalization.
• arm_reshape_f16functionReshape by copying data without changing element order.

function

arm_transpose_f32

C

Transpose a floating-point tensor.

Include/arm_nnfunctions_flt.h:1135

arm_cmsis_nn_status arm_transpose_f32(
    const cmsis_nn_context *ctx,
    const cmsis_nn_transpose_params_f32 *params,
    const cmsis_nn_dims *input_dims,
    const float32_t *input,
    const cmsis_nn_dims *output_dims,
    float32_t *output
)

Transpose a floating-point tensor.

Parameters

Parameters of arm_transpose_f32

Name	Type	Direction	Description
ctx	const cmsis_nn_context *	in, out	Function context that may hold a temporary scratch buffer.
params	const cmsis_nn_transpose_params_f32 *	in	Transpose parameters, including permutation and layout information. num_dims must be in [1, 4] and perm must be a bijection over [0, num_dims - 1].
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions.
input	const float32_t *	in	Pointer to the input tensor data.
output_dims	const cmsis_nn_dims *	in	Output tensor dimensions. The first params->num_dims fields, taken in the order [N, H, W, C], must satisfy output[i] == input[perm[i]]; the function returns `ARM_CMSIS_NN_ARG_ERROR` and writes nothing if they do not.
output	float32_t *	out	Pointer to the output tensor data.

Returns

Returns of arm_transpose_f32

Description
`ARM_CMSIS_NN_SUCCESS` on success or `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments.

function

arm_concatenation_f32_x

C

Concatenate tensors along the X axis.

Include/arm_nnfunctions_flt.h:1158

void arm_concatenation_f32_x(
    const float32_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float32_t *output,
    int32_t output_x,
    uint32_t offset_x
)

Concatenate tensors along the X axis.

Call once per input tensor: offset_x selects where the input is stored along the X axis of the output tensor and must be advanced by input_x after each call. The output tensor must have the same height, channels and batch size as every input tensor.

Parameters

Parameters of arm_concatenation_f32_x

Name	Type	Direction	Description
input	const float32_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float32_t *	out	Pointer to the output tensor.
output_x	int32_t	in	Width of the output tensor.
offset_x	uint32_t	in	Offset on the X axis at which the input tensor is stored. Must be less than `output_x`.

function

arm_concatenation_f32_y

C

Concatenate tensors along the Y axis.

Include/arm_nnfunctions_flt.h:1183

void arm_concatenation_f32_y(
    const float32_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float32_t *output,
    int32_t output_y,
    uint32_t offset_y
)

Concatenate tensors along the Y axis.

Call once per input tensor: offset_y selects where the input is stored along the Y axis of the output tensor and must be advanced by input_y after each call. The output tensor must have the same width, channels and batch size as every input tensor.

Parameters

Parameters of arm_concatenation_f32_y

Name	Type	Direction	Description
input	const float32_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float32_t *	out	Pointer to the output tensor.
output_y	int32_t	in	Height of the output tensor.
offset_y	uint32_t	in	Offset on the Y axis at which the input tensor is stored. Must be less than `output_y`.

function

arm_concatenation_f32_z

C

Concatenate tensors along the Z axis.

Include/arm_nnfunctions_flt.h:1208

void arm_concatenation_f32_z(
    const float32_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float32_t *output,
    int32_t output_z,
    uint32_t offset_z
)

Concatenate tensors along the Z axis.

Call once per input tensor: offset_z selects where the input is stored along the Z axis of the output tensor and must be advanced by input_z after each call. The output tensor must have the same width, height and batch size as every input tensor.

Parameters

Parameters of arm_concatenation_f32_z

Name	Type	Direction	Description
input	const float32_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float32_t *	out	Pointer to the output tensor.
output_z	int32_t	in	Channels in the output tensor.
offset_z	uint32_t	in	Offset on the Z axis at which the input tensor is stored. Must be less than `output_z`.

function

arm_concatenation_f32_w

C

Concatenate tensors along the W axis.

Include/arm_nnfunctions_flt.h:1232

void arm_concatenation_f32_w(
    const float32_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float32_t *output,
    uint32_t offset_w
)

Concatenate tensors along the W axis.

Call once per input tensor: offset_w selects where the input is stored along the W axis of the output tensor and must be advanced by input_w after each call. The output tensor must have the same width, height and channels as every input tensor.

Parameters

Parameters of arm_concatenation_f32_w

Name	Type	Direction	Description
input	const float32_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float32_t *	out	Pointer to the output tensor.
offset_w	uint32_t	in	Offset on the W axis at which the input tensor is stored.

function

arm_concatenation_f32

C

Concatenate float32 tensors of any rank along one axis.

Include/arm_nnfunctions_flt.h:1259

arm_cmsis_nn_status arm_concatenation_f32(
    const float32_t *const *input_data,
    int32_t num_inputs,
    const int32_t *axis_sizes,
    int32_t output_dims,
    const int32_t *output_shape,
    int32_t axis,
    float32_t *output_data
)

Concatenate float32 tensors of any rank along one axis.

Rank-agnostic sibling of the 4-D per-axis arm_concatenation_f32_{x,y,z,w} entry points: all inputs at once, any rank, any axis. Bit copy, NaN/Inf/-0/subnormal payloads preserved. Input s has the output shape with output_shape[axis] replaced by axis_sizes[s]; the inputs are laid down in order along the axis. Inputs must not overlap the output. A dimension of 0 is accepted and copies nothing.

Parameters

Parameters of arm_concatenation_f32

Name	Type	Direction	Description
input_data	const float32_t *const *	in	Array of `num_inputs` pointers to the flattened (row-major) inputs.
num_inputs	int32_t	in	Number of inputs (>= 1).
axis_sizes	const int32_t *	in	Array of length `num_inputs:` each input's extent along `axis`.
output_dims	int32_t	in	Number of dimensions in `output_shape` (>= 1).
output_shape	const int32_t *	in	Output shape; `output_shape`[axis] must equal the sum of `axis_sizes`.
axis	int32_t	in	Axis to concatenate along (0 <= axis < output_dims).
output_data	float32_t *	out	Pointer to the flattened output.

Returns

Returns of arm_concatenation_f32

Description
`ARM_CMSIS_NN_SUCCESS`, or `ARM_CMSIS_NN_ARG_ERROR` (output untouched) on an invalid rank, axis, shape entry, size entry, size sum, NULL pointer or an element count above INT32_MAX.

function

arm_split_f32

C

Split a float32 tensor of any rank into several tensors along one axis.

Include/arm_nnfunctions_flt.h:1285

arm_cmsis_nn_status arm_split_f32(
    const float32_t *input_data,
    int32_t input_dims,
    const int32_t *input_shape,
    int32_t axis,
    int32_t num_splits,
    const int32_t *split_dims,
    float32_t *const *output_data
)

Split a float32 tensor of any rank into several tensors along one axis.

Inverse of arm_concatenation_f32; per-split lengths also cover SPLIT_V. Output s has the input shape with input_shape[axis] replaced by split_dims[s]. Bit copy, NaN/Inf/-0/subnormal payloads preserved. Outputs must not overlap the input. A dimension of 0 is accepted and copies nothing.

Parameters

Parameters of arm_split_f32

Name	Type	Direction	Description
input_data	const float32_t *	in	Pointer to the flattened (row-major) input.
input_dims	int32_t	in	Number of dimensions in `input_shape` (>= 1).
input_shape	const int32_t *	in	Input shape; `input_shape`[axis] must equal the sum of `split_dims`.
axis	int32_t	in	Axis to split along (0 <= axis < input_dims).
num_splits	int32_t	in	Number of outputs (>= 1).
split_dims	const int32_t *	in	Array of length `num_splits:` each output's extent along `axis`.
output_data	float32_t *const *	out	Array of `num_splits` pointers to the flattened outputs.

Returns

Returns of arm_split_f32

Description
`ARM_CMSIS_NN_SUCCESS`, or `ARM_CMSIS_NN_ARG_ERROR` (outputs untouched) on an invalid rank, axis, shape entry, split entry, split sum, NULL pointer or an element count above INT32_MAX.

function

arm_pack_f32

C

Stack float32 tensors of equal shape along a new axis (TFLite PACK).

Include/arm_nnfunctions_flt.h:1310

arm_cmsis_nn_status arm_pack_f32(
    const float32_t *const *input_data,
    int32_t num_inputs,
    int32_t input_dims,
    const int32_t *input_shape,
    int32_t axis,
    float32_t *output_data
)

Stack float32 tensors of equal shape along a new axis (TFLite PACK).

The output shape is input_shape with num_inputs inserted at axis; input s lands at index s of that axis. Bit copy, NaN/Inf/-0/subnormal payloads preserved. Inputs must not overlap the output. Rank-0 inputs (input_dims == 0, axis == 0) stack into a vector.

Parameters

Parameters of arm_pack_f32

Name	Type	Direction	Description
input_data	const float32_t *const *	in	Array of `num_inputs` pointers to the flattened (row-major) inputs.
num_inputs	int32_t	in	Number of inputs (>= 1).
input_dims	int32_t	in	Number of dimensions of each input (>= 0).
input_shape	const int32_t *	in	Shape shared by every input (may be NULL when `input_dims` is 0).
axis	int32_t	in	Position of the new axis in the output (0 <= axis <= input_dims).
output_data	float32_t *	out	Pointer to the flattened output.

Returns

Returns of arm_pack_f32

Description
`ARM_CMSIS_NN_SUCCESS`, or `ARM_CMSIS_NN_ARG_ERROR` (output untouched) on an invalid rank, axis, shape entry, NULL pointer or an element count above INT32_MAX.

function

arm_unpack_f32

C

Unstack a float32 tensor along one axis into inputshape[axis] tensors (TFLite UNPACK).

Include/arm_nnfunctions_flt.h:1334

arm_cmsis_nn_status arm_unpack_f32(
    const float32_t *input_data,
    int32_t input_dims,
    const int32_t *input_shape,
    int32_t axis,
    float32_t *const *output_data
)

Unstack a float32 tensor along one axis into input_shape[axis] tensors (TFLite UNPACK).

Inverse of arm_pack_f32: output s is the input with the axis fixed at index s and removed from the shape. Bit copy, NaN/Inf/-0/subnormal payloads preserved. Outputs must not overlap the input.

Parameters

Parameters of arm_unpack_f32

Name	Type	Direction	Description
input_data	const float32_t *	in	Pointer to the flattened (row-major) input.
input_dims	int32_t	in	Number of dimensions in `input_shape` (>= 1).
input_shape	const int32_t *	in	Input shape; `input_shape`[axis] (>= 1) is the number of outputs.
axis	int32_t	in	Axis to unstack (0 <= axis < input_dims).
output_data	float32_t *const *	out	Array of `input_shape`[axis] pointers to the flattened outputs.

Returns

Returns of arm_unpack_f32

Description
`ARM_CMSIS_NN_SUCCESS`, or `ARM_CMSIS_NN_ARG_ERROR` (outputs untouched) on an invalid rank, axis, shape entry, a zero-extent unstack axis (no outputs to produce), NULL pointer or an element count above INT32_MAX.

function

arm_batch_norm_f32

C

Apply batch normalization.

Include/arm_nnfunctions_flt.h:1390

arm_cmsis_nn_status arm_batch_norm_f32(
    const float32_t *input,
    float32_t *output,
    const float32_t *scale,
    const float32_t *bias,
    const cmsis_nn_dims *input_dims,
    arm_nn_tensor_layout layout
)

Apply batch normalization.

Computes output = input * scale[c] + bias[c] for every element of channel c, with scale and bias holding the pre-folded per-channel factors.

Parameters

Parameters of arm_batch_norm_f32

Name	Type	Direction	Description
input	const float32_t *	in	Pointer to the input tensor data. Format: [N, H, W, C].
output	float32_t *	out	Pointer to the output tensor data, same shape as `input`.
scale	const float32_t *	in	Per-channel scale, `input_dims->c` values.
bias	const float32_t *	in	Per-channel bias, `input_dims->c` values.
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions. Every dimension must be positive.
layout	arm_nn_tensor_layout	in	Tensor layout selector. Must be `ARM_NN_LAYOUT_NHWC`.

Returns

Returns of arm_batch_norm_f32

Description
`ARM_CMSIS_NN_SUCCESS` on success or `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments.

function

arm_reshape_f32

C

Reshape by copying data without changing element order.

Include/arm_nnfunctions_flt.h:1404

void arm_reshape_f32(const float32_t *input, float32_t *output, uint32_t total_size)

Reshape by copying data without changing element order.

Parameters

Parameters of arm_reshape_f32

Name	Type	Direction	Description
input	const float32_t *	in	Pointer to the input tensor data.
output	float32_t *	out	Pointer to the output tensor data. Nothing is copied when it aliases `input`.
total_size	uint32_t	in	Number of elements to copy.

function

arm_transpose_f16

C

Transpose a floating-point tensor.

Include/arm_nnfunctions_flt.h:3161

arm_cmsis_nn_status arm_transpose_f16(
    const cmsis_nn_context *ctx,
    const cmsis_nn_transpose_params_f16 *params,
    const cmsis_nn_dims *input_dims,
    const float16_t *input,
    const cmsis_nn_dims *output_dims,
    float16_t *output
)

Transpose a floating-point tensor.

Parameters

Parameters of arm_transpose_f16

Name	Type	Direction	Description
ctx	const cmsis_nn_context *	in, out	Function context that may hold a temporary scratch buffer.
params	const cmsis_nn_transpose_params_f16 *	in	Transpose parameters, including permutation and layout information. num_dims must be in [1, 4] and perm must be a bijection over [0, num_dims - 1].
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions.
input	const float16_t *	in	Pointer to the input tensor data.
output_dims	const cmsis_nn_dims *	in	Output tensor dimensions. The first params->num_dims fields, taken in the order [N, H, W, C], must satisfy output[i] == input[perm[i]]; the function returns `ARM_CMSIS_NN_ARG_ERROR` and writes nothing if they do not.
output	float16_t *	out	Pointer to the output tensor data.

Returns

Returns of arm_transpose_f16

Description
`ARM_CMSIS_NN_SUCCESS` on success or `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments.

function

arm_concatenation_f16_x

C

Concatenate tensors along the X axis.

Include/arm_nnfunctions_flt.h:3171

void arm_concatenation_f16_x(
    const float16_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float16_t *output,
    int32_t output_x,
    uint32_t offset_x
)

Concatenate tensors along the X axis.

Call once per input tensor: offset_x selects where the input is stored along the X axis of the output tensor and must be advanced by input_x after each call. The output tensor must have the same height, channels and batch size as every input tensor.

Parameters

Parameters of arm_concatenation_f16_x

Name	Type	Direction	Description
input	const float16_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float16_t *	out	Pointer to the output tensor.
output_x	int32_t	in	Width of the output tensor.
offset_x	uint32_t	in	Offset on the X axis at which the input tensor is stored. Must be less than `output_x`.

function

arm_concatenation_f16_y

C

Concatenate tensors along the Y axis.

Include/arm_nnfunctions_flt.h:3183

void arm_concatenation_f16_y(
    const float16_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float16_t *output,
    int32_t output_y,
    uint32_t offset_y
)

Concatenate tensors along the Y axis.

Call once per input tensor: offset_y selects where the input is stored along the Y axis of the output tensor and must be advanced by input_y after each call. The output tensor must have the same width, channels and batch size as every input tensor.

Parameters

Parameters of arm_concatenation_f16_y

Name	Type	Direction	Description
input	const float16_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float16_t *	out	Pointer to the output tensor.
output_y	int32_t	in	Height of the output tensor.
offset_y	uint32_t	in	Offset on the Y axis at which the input tensor is stored. Must be less than `output_y`.

function

arm_concatenation_f16_z

C

Concatenate tensors along the Z axis.

Include/arm_nnfunctions_flt.h:3195

void arm_concatenation_f16_z(
    const float16_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float16_t *output,
    int32_t output_z,
    uint32_t offset_z
)

Concatenate tensors along the Z axis.

Call once per input tensor: offset_z selects where the input is stored along the Z axis of the output tensor and must be advanced by input_z after each call. The output tensor must have the same width, height and batch size as every input tensor.

Parameters

Parameters of arm_concatenation_f16_z

Name	Type	Direction	Description
input	const float16_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float16_t *	out	Pointer to the output tensor.
output_z	int32_t	in	Channels in the output tensor.
offset_z	uint32_t	in	Offset on the Z axis at which the input tensor is stored. Must be less than `output_z`.

function

arm_concatenation_f16_w

C

Concatenate tensors along the W axis.

Include/arm_nnfunctions_flt.h:3207

void arm_concatenation_f16_w(
    const float16_t *input,
    int32_t input_x,
    int32_t input_y,
    int32_t input_z,
    int32_t input_w,
    float16_t *output,
    uint32_t offset_w
)

Concatenate tensors along the W axis.

Call once per input tensor: offset_w selects where the input is stored along the W axis of the output tensor and must be advanced by input_w after each call. The output tensor must have the same width, height and channels as every input tensor.

Parameters

Parameters of arm_concatenation_f16_w

Name	Type	Direction	Description
input	const float16_t *	in	Pointer to the input tensor. Must not overlap the output tensor.
input_x	int32_t	in	Width of the input tensor.
input_y	int32_t	in	Height of the input tensor.
input_z	int32_t	in	Channels in the input tensor.
input_w	int32_t	in	Batch size in the input tensor.
output	float16_t *	out	Pointer to the output tensor.
offset_w	uint32_t	in	Offset on the W axis at which the input tensor is stored.

function

arm_concatenation_f16

C

Concatenate float32 tensors of any rank along one axis.

Include/arm_nnfunctions_flt.h:3218

arm_cmsis_nn_status arm_concatenation_f16(
    const float16_t *const *input_data,
    int32_t num_inputs,
    const int32_t *axis_sizes,
    int32_t output_dims,
    const int32_t *output_shape,
    int32_t axis,
    float16_t *output_data
)

Concatenate float32 tensors of any rank along one axis.

Rank-agnostic sibling of the 4-D per-axis arm_concatenation_f32_{x,y,z,w} entry points: all inputs at once, any rank, any axis. Bit copy, NaN/Inf/-0/subnormal payloads preserved. Input s has the output shape with output_shape[axis] replaced by axis_sizes[s]; the inputs are laid down in order along the axis. Inputs must not overlap the output. A dimension of 0 is accepted and copies nothing.

Parameters

Parameters of arm_concatenation_f16

Name	Type	Direction	Description
input_data	const float16_t *const *	in	Array of `num_inputs` pointers to the flattened (row-major) inputs.
num_inputs	int32_t	in	Number of inputs (>= 1).
axis_sizes	const int32_t *	in	Array of length `num_inputs:` each input's extent along `axis`.
output_dims	int32_t	in	Number of dimensions in `output_shape` (>= 1).
output_shape	const int32_t *	in	Output shape; `output_shape`[axis] must equal the sum of `axis_sizes`.
axis	int32_t	in	Axis to concatenate along (0 <= axis < output_dims).
output_data	float16_t *	out	Pointer to the flattened output.

Returns

Returns of arm_concatenation_f16

Description
`ARM_CMSIS_NN_SUCCESS`, or `ARM_CMSIS_NN_ARG_ERROR` (output untouched) on an invalid rank, axis, shape entry, size entry, size sum, NULL pointer or an element count above INT32_MAX.

function

arm_pack_f16

C

Stack float32 tensors of equal shape along a new axis (TFLite PACK).

Include/arm_nnfunctions_flt.h:3229

arm_cmsis_nn_status arm_pack_f16(
    const float16_t *const *input_data,
    int32_t num_inputs,
    int32_t input_dims,
    const int32_t *input_shape,
    int32_t axis,
    float16_t *output_data
)

Stack float32 tensors of equal shape along a new axis (TFLite PACK).

The output shape is input_shape with num_inputs inserted at axis; input s lands at index s of that axis. Bit copy, NaN/Inf/-0/subnormal payloads preserved. Inputs must not overlap the output. Rank-0 inputs (input_dims == 0, axis == 0) stack into a vector.

Parameters

Parameters of arm_pack_f16

Name	Type	Direction	Description
input_data	const float16_t *const *	in	Array of `num_inputs` pointers to the flattened (row-major) inputs.
num_inputs	int32_t	in	Number of inputs (>= 1).
input_dims	int32_t	in	Number of dimensions of each input (>= 0).
input_shape	const int32_t *	in	Shape shared by every input (may be NULL when `input_dims` is 0).
axis	int32_t	in	Position of the new axis in the output (0 <= axis <= input_dims).
output_data	float16_t *	out	Pointer to the flattened output.

Returns

Returns of arm_pack_f16

Description
`ARM_CMSIS_NN_SUCCESS`, or `ARM_CMSIS_NN_ARG_ERROR` (output untouched) on an invalid rank, axis, shape entry, NULL pointer or an element count above INT32_MAX.

function

arm_unpack_f16

C

Unstack a float32 tensor along one axis into inputshape[axis] tensors (TFLite UNPACK).

Include/arm_nnfunctions_flt.h:3239

arm_cmsis_nn_status arm_unpack_f16(
    const float16_t *input_data,
    int32_t input_dims,
    const int32_t *input_shape,
    int32_t axis,
    float16_t *const *output_data
)

Unstack a float32 tensor along one axis into input_shape[axis] tensors (TFLite UNPACK).

Inverse of arm_pack_f32: output s is the input with the axis fixed at index s and removed from the shape. Bit copy, NaN/Inf/-0/subnormal payloads preserved. Outputs must not overlap the input.

Parameters

Parameters of arm_unpack_f16

Name	Type	Direction	Description
input_data	const float16_t *	in	Pointer to the flattened (row-major) input.
input_dims	int32_t	in	Number of dimensions in `input_shape` (>= 1).
input_shape	const int32_t *	in	Input shape; `input_shape`[axis] (>= 1) is the number of outputs.
axis	int32_t	in	Axis to unstack (0 <= axis < input_dims).
output_data	float16_t *const *	out	Array of `input_shape`[axis] pointers to the flattened outputs.

Returns

Returns of arm_unpack_f16

Description
`ARM_CMSIS_NN_SUCCESS`, or `ARM_CMSIS_NN_ARG_ERROR` (outputs untouched) on an invalid rank, axis, shape entry, a zero-extent unstack axis (no outputs to produce), NULL pointer or an element count above INT32_MAX.

function

arm_batch_norm_f16

C

Apply batch normalization.

Include/arm_nnfunctions_flt.h:3272

arm_cmsis_nn_status arm_batch_norm_f16(
    const float16_t *input,
    float16_t *output,
    const float16_t *scale,
    const float16_t *bias,
    const cmsis_nn_dims *input_dims,
    arm_nn_tensor_layout layout
)

Apply batch normalization.

Computes output = input * scale[c] + bias[c] for every element of channel c, with scale and bias holding the pre-folded per-channel factors.

Parameters

Parameters of arm_batch_norm_f16

Name	Type	Direction	Description
input	const float16_t *	in	Pointer to the input tensor data. Format: [N, H, W, C].
output	float16_t *	out	Pointer to the output tensor data, same shape as `input`.
scale	const float16_t *	in	Per-channel scale, `input_dims->c` values.
bias	const float16_t *	in	Per-channel bias, `input_dims->c` values.
input_dims	const cmsis_nn_dims *	in	Input tensor dimensions. Every dimension must be positive.
layout	arm_nn_tensor_layout	in	Tensor layout selector. Must be `ARM_NN_LAYOUT_NHWC`.

Returns

Returns of arm_batch_norm_f16

Description
`ARM_CMSIS_NN_SUCCESS` on success or `ARM_CMSIS_NN_ARG_ERROR` on invalid arguments.

function

arm_reshape_f16

C

Reshape by copying data without changing element order.

Include/arm_nnfunctions_flt.h:3282

void arm_reshape_f16(const float16_t *input, float16_t *output, uint32_t total_size)

Reshape by copying data without changing element order.

Parameters

Parameters of arm_reshape_f16

Name	Type	Direction	Description
input	const float16_t *	in	Pointer to the input tensor data.
output	float16_t *	out	Pointer to the output tensor data. Nothing is copied when it aliases `input`.
total_size	uint32_t	in	Number of elements to copy.