Files  
file  NeuralNetworks.h 
Data Structures  
struct  ANeuralNetworksOperandType 
Typedefs  
typedef struct ANeuralNetworksMemory  ANeuralNetworksMemory 
typedef struct ANeuralNetworksModel  ANeuralNetworksModel 
typedef struct ANeuralNetworksCompilation  ANeuralNetworksCompilation 
typedef struct ANeuralNetworksExecution  ANeuralNetworksExecution 
typedef struct ANeuralNetworksOperandType  ANeuralNetworksOperandType 
typedef int32_t  ANeuralNetworksOperationType 
typedef struct ANeuralNetworksEvent  ANeuralNetworksEvent 
Detailed Description
Typedef Documentation
◆ ANeuralNetworksCompilation
typedef struct ANeuralNetworksCompilation ANeuralNetworksCompilation 
ANeuralNetworksCompilation is an opaque type that can be used to compile a machine learning model.
To use:
 Create a new compilation instance by calling the ANeuralNetworksCompilation_create function.
 Set any desired properties on the compilation (for example, ANeuralNetworksCompilation_setPreference).
 Complete the compilation with ANeuralNetworksCompilation_finish.
 Use the compilation as many times as needed with ANeuralNetworksExecution_create.
 Destroy the compilation with ANeuralNetworksCompilation_free once all executions using the compilation have completed.
A compilation is completed by calling ANeuralNetworksCompilation_finish. A compilation is destroyed by calling ANeuralNetworksCompilation_free.
A compilation cannot be modified once ANeuralNetworksCompilation_finish has been called on it.
It is the application's responsibility to make sure that only one thread modifies a compilation at a given time. It is however safe for more than one thread to use the compilation once ANeuralNetworksCompilation_finish has returned.
It is also the application's responsibility to ensure that there are no other uses of the compilation after calling ANeuralNetworksCompilation_free. This includes any execution object created using the compilation.
◆ ANeuralNetworksEvent
typedef struct ANeuralNetworksEvent ANeuralNetworksEvent 
ANeuralNetworksEvent is an opaque type that represents an event that will be signaled once an execution completes.
◆ ANeuralNetworksExecution
typedef struct ANeuralNetworksExecution ANeuralNetworksExecution 
ANeuralNetworksExecution is an opaque type that can be used to apply a machine learning model to a set of inputs.
To use:
 Create a new execution instance by calling the ANeuralNetworksExecution_create function.
 Associate data to the model inputs with ANeuralNetworksExecution_setInput or ANeuralNetworksExecution_setInputFromMemory.
 Associate output buffers to the model outputs with ANeuralNetworksExecution_setOutput or ANeuralNetworksExecution_setOutputFromMemory.
 Apply the model with ANeuralNetworksExecution_startCompute.
 Wait for the execution to complete with ANeuralNetworksEvent_wait.
 Destroy the execution with ANeuralNetworksExecution_free.
An execution cannot be modified once ANeuralNetworksExecution_startCompute has been called on it.
An execution can be applied to a model with ANeuralNetworksExecution_startCompute only once. Create new executions to do new evaluations of the model.
It is the application's responsibility to make sure that only one thread modifies an execution at a given time. It is however safe for more than one thread to use ANeuralNetworksEvent_wait at the same time.
It is also the application's responsibility to ensure that there are no other uses of the request after calling ANeuralNetworksExecution_free.
◆ ANeuralNetworksMemory
typedef struct ANeuralNetworksMemory ANeuralNetworksMemory 
ANeuralNetworksMemory is an opaque type that represents memory.
This type is used to represent shared memory, memory mapped files, and similar memories.
By using shared memory, a program can efficiently communicate to the runtime and drivers the tensors that define a model. See ANeuralNetworksModel_setOperandValueFromMemory. An application should typically create one shared memory object that contains every tensor needed to define a model. ANeuralNetworksMemory_createFromFd can be used to create shared memory from a file handle. ANeuralNetworksMemory_createShared can be used to directly created shared memory.
Memory objects can also be used to specify the input and output arguments of an execution. See ANeuralNetworksExecution_setInputFromMemory and ANeuralNetworksExecution_setOutputFromMemory.
◆ ANeuralNetworksModel
typedef struct ANeuralNetworksModel ANeuralNetworksModel 
ANeuralNetworksModel is an opaque type that contains a description of the mathematical operations that constitute the model.
Build the model by calling
A model is completed by calling ANeuralNetworksModel_finish. A model is destroyed by calling ANeuralNetworksModel_free.
A model cannot be modified once ANeuralNetworksModel_finish has been called on it.
It is the application's responsibility to make sure that only one thread modifies a model at a given time. It is however safe for more than one thread to use the model once ANeuralNetworksModel_finish has returned.
It is also the application's responsibility to ensure that there are no other uses of the model after calling ANeuralNetworksModel_free. This includes any compilation or execution object created using the model.
◆ ANeuralNetworksOperandType
typedef struct ANeuralNetworksOperandType ANeuralNetworksOperandType 
ANeuralNetworksOperandType describes the type of an operand. This structure is used to describe both scalars and tensors.
◆ ANeuralNetworksOperationType
typedef int32_t ANeuralNetworksOperationType 
Enumeration Type Documentation
◆ anonymous enum
anonymous enum 
For ANeuralNetworksModel_setOperandValue, values with a length smaller or equal to this will be immediately copied into the model. The size is in bytes.
Enumerator  

ANEURALNETWORKS_MAX_SIZE_OF_IMMEDIATELY_COPIED_VALUES 
◆ FuseCode
enum FuseCode 
◆ OperandCode
enum OperandCode 
Operand types.
The type of operands that can be added to a model.
Although we define many types, most operators accept just a few types. Most used are ANEURALNETWORKS_TENSOR_FLOAT32, ANEURALNETWORKS_TENSOR_QUANT8_ASYMM, and ANEURALNETWORKS_INT32.
◆ OperationCode
enum OperationCode 
Operation types.
The type of operations that can be added to a model.
Enumerator  

ANEURALNETWORKS_ADD  Adds two tensors, elementwise. Takes two input tensors of identical type and compatible dimensions. The output is the sum of both input tensors, optionally modified by an activation function. Two dimensions are compatible when:
The size of the output is the maximum size along each dimension of the input operands. It starts with the trailing dimensions, and works its way forward. Example: input1.dimension = {4, 1, 2} input2.dimension = {5, 4, 3, 1} output.dimension = {5, 4, 3, 2} Supported tensor types: Supported tensor rank: up to 4 Inputs:
Outputs:

ANEURALNETWORKS_AVERAGE_POOL_2D  Performs a 2D average pooling operation. The output dimensions are functions of the filter dimensions, stride, and padding. The values in the output tensor are computed as: output[batch, row, col, channel] = sum_{i, j}(input[batch, row + i, col + j, channel]) / sum(1) Supported tensor types: Supported tensor rank: 4, with "NHWC" (i.e., Num_samples, Height, Width, and Channels) data layout. Both explicit padding and implicit padding are supported. Inputs (explicit padding):
Inputs (implicit padding):
Outputs:

ANEURALNETWORKS_CONCATENATION  Concatenates the input tensors along the given dimension. The input tensors must have identical type and the same dimensions except the dimension along the concatenation axis. Supported tensor types: Supported tensor rank: up to 4 Inputs:
Outputs:

ANEURALNETWORKS_CONV_2D  Performs an 2D convolution operation. The CONV_2D op sweeps a 2D filter that can mix channels together over a batch of images, applying the filter to each window of each image of the appropriate size. The output dimensions are functions of the filter dimensions, stride, and padding. The values in the output tensor are computed as: output[batch, row, col, channel] = sum_{i, j} ( input[batch, row + i, col + j, k] * filter[channel, row + i, col + j, k] + bias[channel] ) Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Both explicit padding and implicit padding are supported. Inputs (explicit padding):
Inputs (implicit padding):
Outputs:

ANEURALNETWORKS_DEPTHWISE_CONV_2D  Performs a depthwise 2D convolution operation. Given an input tensor of shape [batches, height, width, depth_in] and a filter tensor of shape [1, filter_height, filter_width, depth_out] containing depth_out convolutional filters of depth 1, DEPTHWISE_CONV applies a different filter to each input channel (expanding from 1 channel to channel_multiplier channels for each), then concatenates the results together. The output has depth_out = depth_in * depth_multiplier channels. The output dimensions are functions of the filter dimensions, stride, and padding. The values in the output tensor are computed as: output[b, i, j, k * channel_multiplier + q] = sum_{di, dj} ( input[b, strides[1] * i + di, strides[2] * j + dj, k] * filter[1, di, dj, k * channel_multiplier + q] ) Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Both explicit padding and implicit padding are supported. Inputs (explicit padding):
Inputs (implicit padding):
Outputs:

ANEURALNETWORKS_DEPTH_TO_SPACE  Rearranges data from depth into blocks of spatial data. More specifically, this op outputs a copy of the input tensor where values from the depth dimension are moved in spatial blocks to the height and width dimensions. The value block_size indicates the input block size and how the data is moved. Chunks of data of size block_size * block_size from depth are rearranged into nonoverlapping blocks of size block_size x block_size. The width of the output tensor is input_depth * block_size, whereas the height is input_height * block_size. The depth of the input tensor must be divisible by block_size * block_size Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Inputs:
Outputs:

ANEURALNETWORKS_DEQUANTIZE  Dequantizes the input tensor. The formula is: output = (input  zeroPoint) * scale. Supported tensor types: Supported tensor rank: up to 4 Inputs:
Outputs:

ANEURALNETWORKS_EMBEDDING_LOOKUP  Looks up subtensors in the input tensor. This operator takes for input a tensor of values (Values) and a onedimensional tensor of selection indices (Lookups). The output tensor is the concatenation of subtensors of Values as selected by Lookups. Think of Values as being sliced along its first dimension: The entries in Lookups select which slices are concatenated together to create the output tensor. For example, if Values has shape of [40, 200, 300] and Lookups has shape of [3], we would expect all three values found in Lookups to be between 0 and 39. The resulting tensor will have shape of [3, 200, 300]. If a value in Lookups is out of bounds, the operation will fail and an error will be reported. Inputs:
Output:

ANEURALNETWORKS_FLOOR  Computes elementwise floor() on the input tensor. Supported tensor types: Supported tensor rank: up to 4 Inputs:
Outputs:

ANEURALNETWORKS_FULLY_CONNECTED  Denotes a fully (densely) connected layer, which connects all elements in the input tensor with each element in the output tensor. This layer implements the operation: outputs = activation(inputs * weights’ + bias) Supported tensor types: Supported tensor rank: up to 4. Inputs:
Outputs:

ANEURALNETWORKS_HASHTABLE_LOOKUP  Looks up subtensors in the input tensor using a keyvalue map. This operator takes for input a tensor of values (Values), a onedimensional tensor of selection values (Lookups) and a onedimensional tensor that maps these values to Values indexes. The output tensor is the concatenation of subtensors of Values as selected by Lookups via Keys. Think of Values as being sliced along its outermost dimension. The output is a concatenation of selected slices, with one slice for each entry of Lookups. The slice selected is the one at the same index as the Maps entry that matches the value in Lookups. For a hit, the corresponding subtensor of Values is included in the Output tensor. For a miss, the corresponding subtensor in Output will have zero values. For example, if Values has shape of [40, 200, 300], Keys should have a shape of [40]. If Lookups tensor has shape of [3], we're concatenating three slices, so the resulting tensor will have the shape of [3, 200, 300]. If the first entry in Lookups has the value 123456, we'll look for that value in Keys tensor. If the sixth entry of Keys contains 123456, we'll select the sixth slice of Values. If no entry in Keys has 123456, a slice of zeroes will be concatenated. Inputs:
Outputs:

ANEURALNETWORKS_L2_NORMALIZATION  Applies L2 normalization along the depth dimension. The values in the output tensor are computed as: output[batch, row, col, channel] = input[batch, row, col, channel] / sqrt(sum_{c} pow(input[batch, row, col, c], 2)) For input tensor with more dimensions, independently normalizes each 1D slice along dimension dim. Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout (i.e., Num_samples, Height, Width, and Channels). Inputs:
Outputs:

ANEURALNETWORKS_L2_POOL_2D  Performs an 2D L2 pooling operation. The output dimensions are functions of the filter dimensions, stride, and padding. The values in the output tensor are computed as: output[batch, row, col, channel] = sqrt(sum_{i, j} pow(input[batch, row + i, col + j, channel], 2) / sum(1)) Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Both explicit padding and implicit padding are supported. Inputs (explicit padding):
Inputs (implicit padding):
Outputs:

ANEURALNETWORKS_LOCAL_RESPONSE_NORMALIZATION  Applies Local Response Normalization along the depth dimension. The 4D input tensor is treated as a 3D array of 1D vectors (along the last dimension), and each vector is normalized independently. Within a given vector, each component is divided by the weighted, squared sum of inputs within depth_radius. The output is calculated using this formula: sqr_sum[a, b, c, d] = sum(pow(input[a, b, c, d  depth_radius : d + depth_radius + 1], 2) output = input / pow((bias + alpha * sqr_sum), beta) Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Inputs:
Outputs:

ANEURALNETWORKS_LOGISTIC  Computes sigmoid activation on the input tensor elementwise. The output is calculated using this formula: output = 1 / (1 + exp(input)) Supported tensor types: Supported tensor rank: up to 4. Inputs:
Outputs:

ANEURALNETWORKS_LSH_PROJECTION  Projects an input to a bit vector via locality senstive hashing. Inputs:
Outputs:

ANEURALNETWORKS_LSTM  Performs a single time step in a Long ShortTerm Memory (LSTM) layer The LSTM operation is described by the following equations.
Where:
The operation has the following independently optional inputs:
References: The default nonpeephole nonCIFG implementation is based on: http://www.bioinf.jku.at/publications/older/2604.pdf S. Hochreiter and J. Schmidhuber. "Long ShortTerm Memory". Neural Computation, 9(8):17351780, 1997. The peephole implementation and projection layer is based on: https://research.google.com/pubs/archive/43905.pdf Hasim Sak, Andrew Senior, and Francoise Beaufays. "Long shortterm memory recurrent neural network architectures for large scale acoustic modeling." INTERSPEECH, 2014. (However, the concept of peephole optimization was introduced in work prior to this paper.) The coupling of input and forget gate (CIFG) is based on: http://arxiv.org/pdf/1503.04069.pdf Greff et al. "LSTM: A Search Space Odyssey" Supported tensor types (type T): Inputs:
Outputs:

ANEURALNETWORKS_MAX_POOL_2D  Performs an 2D max pooling operation. The output dimensions are functions of the filter dimensions, stride, and padding. The values in the output tensor are computed as: output[batch, row, col, channel] = max_{i, j} (input[batch, row + i, col + j, channel]) Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Both explicit padding and implicit padding are supported. Inputs (explicit padding):
Inputs (implicit padding):
Outputs:

ANEURALNETWORKS_MUL  Multiplies two tensors, elementwise. Takes two input tensors of identical type and compatible dimensions. The output is the product of both input tensors, optionally modified by an activation function. Two dimensions are compatible when:
The size of the resulting output is the maximum size along each dimension of the input operands. It starts with the trailing dimensions, and works its way forward. Supported tensor types: Supported tensor rank: up to 4 Inputs:
Outputs:

ANEURALNETWORKS_RELU  Computes rectified linear activation on the input tensor elementwise. The output is calculated using this formula: output = max(0, input) Supported tensor types: Supported tensor rank: up to 4. Inputs:
Outputs:

ANEURALNETWORKS_RELU1  Computes rectified linear 1 activation on the input tensor elementwise. The output is calculated using this formula: output = min(1.f, max(1.f, input)) Supported tensor types: Supported tensor rank: up to 4. Inputs:
Outputs:

ANEURALNETWORKS_RELU6  Computes rectified linear 6 activation on the input tensor elementwise. The output is calculated using this formula: output = min(6, max(0, input)) Supported tensor types: Supported tensor rank: up to 4. Inputs:
Outputs:

ANEURALNETWORKS_RESHAPE  Reshapes a tensor. Given tensor, this operation returns a tensor that has the same values as tensor, but with a newly specified shape. Supported tensor types: Supported tensor rank: up to 4. Inputs:
Outputs:

ANEURALNETWORKS_RESIZE_BILINEAR  Resizes images to given size using the bilinear interpretation. Resized images will be distorted if their output aspect ratio is not the same as input aspect ratio. Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Inputs:
Outputs:

ANEURALNETWORKS_RNN  A basic recurrent neural network layer. This layer implements the operation: outputs = state = activation(inputs * input_weights + state * recurrent_weights + bias) Where:
Supported tensor types (Type T): Inputs:
Outputs:

ANEURALNETWORKS_SOFTMAX  Computes the softmax activation on the input tensor elementwise, per batch, by normalizing the input vector so the maximum coefficient is zero. The output is calculated using this formula: output[batch, i] = exp((input[batch, i]  max(input[batch, :])) * beta) / sum_{k}{exp((input[batch, k]  max(input[batch, :])) * beta)} Supported tensor types: Supported tensor rank: 2 or 4. Inputs:
Outputs:

ANEURALNETWORKS_SPACE_TO_DEPTH  Rearranges blocks of spatial data, into depth. More specifically, this op outputs a copy of the input tensor where values from the height and width dimensions are moved to the depth dimension. The value block_size indicates the input block size and how the data is moved. Chunks of data of size block_size * block_size from depth are rearranged into nonoverlapping blocks of size block_size x block_size. The depth of the output tensor is input_depth * block_size * block_size. The input tensor's height and width must be divisible by block_size. Supported tensor types: Supported tensor rank: 4, with "NHWC" data layout. Inputs:
Outputs:

ANEURALNETWORKS_SVDF  SVDF op is a kind of stateful layer derived from the notion that a densely connected layer that's processing a sequence of input frames can be approximated by using a singular value decomposition of each of its nodes. The implementation is based on: https://research.google.com/pubs/archive/43813.pdf P. Nakkiran, R. Alvarez, R. Prabhavalkar, C. Parada. “Compressing Deep Neural Networks using a RankConstrained Topology”. INTERSPEECH, 2015. It processes the incoming input using a 2stage filtering mechanism:
Specifically, for rank 1, this layer implements the operation: memory = push(conv1d(inputs, weights_feature, feature_dim, "ANEURALNETWORKS_PADDING_VALID")); outputs = activation(memory * weights_time + bias); Where:
Each rank adds a dimension to the weights matrices by means of stacking the filters. Supported tensor types (type T): Inputs:
Outputs:

ANEURALNETWORKS_TANH  Computes hyperbolic tangent of input tensor elementwise. The output is calculated using this formula: output = tanh(input) Supported tensor types: Supported tensor rank: up to 4. Inputs:
Outputs:

ANEURALNETWORKS_BATCH_TO_SPACE_ND  BatchToSpace for Ndimensional tensors. This operation reshapes the batch dimension (dimension 0) into M + 1 dimensions of shape block_shape + [batch], interleaves these blocks back into the grid defined by the spatial dimensions [1, ..., M], to obtain a result with the same rank as the input. The spatial dimensions of this intermediate result are then optionally cropped according to the amount to crop (input2) to produce the output. This is the reverse of SpaceToBatch. Supported tensor types: Supported tensor rank: 4 Inputs: 0: An nD tensor, specifying the tensor to be reshaped 1: A 1D Tensor of type TENSOR_INT32, the block sizes for each spatial dimension of the input tensor. All values must be >= 1. 2: A 1D Tensor of type TENSOR_INT32, the amount to crop for each spatial diemension of the input tensor. All values must be >= 0. Outputs: 0: A tensor of the same type as input0. 
ANEURALNETWORKS_DIV  Elementwise division of two tensors. Takes two input tensors of identical type and compatible dimensions. The output is the result of dividing the first input tensor by the second, optionally modified by an activation function. Two dimensions are compatible when:
The size of the output is the maximum size along each dimension of the input operands. It starts with the trailing dimensions, and works its way forward. Example: input1.dimension = {4, 1, 2} input2.dimension = {5, 4, 3, 1} output.dimension = {5, 4, 3, 2} Supported tensor types: Supported tensor rank: up to 4 Inputs: 0: An nD tensor, specifying the first input. 1: A tensor of the same type, and compatible dimensions as input0. 2: An INT32 value, and has to be one of the FusedActivationFunc values. Specifies the activation to invoke on the result of each addition. Outputs: 0: A tensor of the same type as input0. 
ANEURALNETWORKS_MEAN  Computes the mean of elements across dimensions of a tensor. Reduces the input tensor along the given dimensions to reduce. Unless keep_dims is true, the rank of the tensor is reduced by 1 for each entry in axis. If keep_dims is true, the reduced dimensions are retained with length 1. If dimensions to reduce have no entries, all dimensions are reduced, and a tensor with a single element is returned. Supported tensor types: Supported tensor rank: up to 4 Inputs: 0: A tensor, specifying the input. 1: A 1D Tensor of type TENSOR_INT32. The dimensions to reduce. If None (the default), reduces all dimensions. Must be in the range [rank(input_tensor), rank(input_tensor)). 2: An INT32 value, keep_dims. If positive, retains reduced dimensions with length 1. Outputs: 0: A tensor of the same type as input0. 
ANEURALNETWORKS_PAD  Pads a tensor. This operation pads a tensor according to the specified paddings. Supported tensor types: Supported tensor rank: up to 4 Inputs: 0: An nD tensor, specifying the tensor to be padded. 1: A 2D Tensor of type TENSOR_INT32, the paddings for each spatial dimension of the input tensor. The shape of the tensor must be {rank(input0), 2}. padding[i, 0] specifies the number of element to be padded in the front of dimension i. padding[i, 1] specifies the number of element to be padded after the end of dimension i. Outputs: 0: A tensor of the same type as input0. 
ANEURALNETWORKS_SPACE_TO_BATCH_ND  SpaceToBatch for NDimensional tensors. This operation divides "spatial" dimensions [1, ..., M] of the input into a grid of blocks of shape block_shape, and interleaves these blocks with the "batch" dimension (0) such that in the output, the spatial dimensions [1, ..., M] correspond to the position within the grid, and the batch dimension combines both the position within a spatial block and the original batch position. Prior to division into blocks, the spatial dimensions of the input are optionally zero padded according to paddings. Supported tensor types: Supported tensor rank: 4 Inputs: 0: An nD tensor, specifying the input. 1: A 1D Tensor of type TENSOR_INT32, the block sizes for each spatial dimension of the input tensor. All values must be >= 1. 2: A 2D Tensor of type TENSOR_INT32, the paddings for each spatial diemension of the input tensor. All values must be >= 0. The shape of the tensor must be {rank(input0), 2}. padding[i, 0] specifies the number of element to be padded in the front of dimension i. padding[i, 1] specifies the number of element to be padded after the end of dimension i. Outputs: 0: A tensor of the same type as input0. 
ANEURALNETWORKS_SQUEEZE  Removes dimensions of size 1 from the shape of a tensor. Given a tensor input, this operation returns a tensor of the same type with all dimensions of size 1 removed. If you don't want to remove all size 1 dimensions, you can remove specific size 1 dimensions by specifying the axes (input1). Supported tensor types: Supported tensor rank: up to 4 Inputs: 0: An nD tensor, the tensor to be squeezed. 1: An optional 1D tensor of type TENSOR_INT32. The dimensions to squeeze. If specified only squeezes the dimensions listed. Otherwise, squeezes all dimensions. The dimension index starts at 0. An error will be reported if squeezing a dimension that is not 1. Outputs: 0: A tensor of the same type as input0. Contains the same data as input, but has one or more dimensions of size 1 removed. 
ANEURALNETWORKS_STRIDED_SLICE  Extracts a strided slice of a tensor. Roughly speaking, this op extracts a slice of size (end  begin) / stride from the given input tensor. Starting at the location specified by begin the slice continues by adding stride to the index until all dimensions are not less than end. Note that a stride can be negative, which causes a reverse slice. Supported tensor types: Supported tensor rank: up to 4 Inputs: 0: An nD tensor, specifying the tensor to be sliced. 1: A 1D Tensor of type TENSOR_INT32, the starts of the dimensions of the input tensor to be sliced. The length must be of rank(input0). 2: A 1D Tensor of type TENSOR_INT32, the ends of the dimensions of the input tensor to be sliced. The length must be of rank(input0). 3: A 1D Tensor of type TENSOR_INT32, the strides of the dimensions of the input tensor to be sliced. The length must be of rank(input0). Outputs: 0: A tensor of the same type as input0. 
ANEURALNETWORKS_SUB  Elementwise subtraction of two tensors. Takes two input tensors of identical type and compatible dimensions. The output is the result of subtracting the second input tensor from the first one, optionally modified by an activation function. Two dimensions are compatible when:
The size of the output is the maximum size along each dimension of the input operands. It starts with the trailing dimensions, and works its way forward. Example: input1.dimension = {4, 1, 2} input2.dimension = {5, 4, 3, 1} output.dimension = {5, 4, 3, 2} Supported tensor types: Supported tensor rank: up to 4 Inputs: 0: An nD tensor, specifying the first input. 1: A tensor of the same type, and compatible dimensions as input0. 2: An INT32 value, and has to be one of the FusedActivationFunc values. Specifies the activation to invoke on the result of each addition. Outputs: 0: A tensor of the same type as input0. 
ANEURALNETWORKS_TRANSPOSE  Transposes the input tensor, permuting the dimensions according to the perm tensor. The returned tensor's dimension i corresponds to the input dimension perm[i]. If perm is not given, it is set to (n1...0), where n is the rank of the input tensor. Hence by default, this operation performs a regular matrix transpose on 2D input Tensors. Supported tensor types: Supported tensor rank: up to 4 Inputs: 0: An nD tensor, specifying the tensor to be transposed. 1: An optional 1D Tensor of type TENSOR_INT32, the permutation of the dimensions of the input tensor. Outputs: 0: A tensor of the same type as input0. 
◆ PaddingCode
enum PaddingCode 
Implicit padding algorithms.
◆ PreferenceCode
enum PreferenceCode 
Execution preferences.
◆ ResultCode
enum ResultCode 
Function Documentation
◆ ANeuralNetworksCompilation_create()
int ANeuralNetworksCompilation_create  (  ANeuralNetworksModel *  model, 
ANeuralNetworksCompilation **  compilation  
) 
Create a ANeuralNetworksCompilation to compile the given model.
This only creates the object. Compilation is only performed once ANeuralNetworksCompilation_finish is invoked.
ANeuralNetworksCompilation_finish should be called once all desired properties have been set on the compilation.
ANeuralNetworksModel_free should be called once the compilation is no longer needed.
The provided model must outlive the compilation.
The model must already have been finished by a call to ANeuralNetworksModel_finish.
See ANeuralNetworksCompilation for information on multithreaded usage.
 Parameters

model The ANeuralNetworksModel to be compiled. compilation The newly created object or NULL if unsuccessful.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful, ANEURALNETWORKS_BAD_DATA if the model is invalid.
◆ ANeuralNetworksCompilation_finish()
int ANeuralNetworksCompilation_finish  (  ANeuralNetworksCompilation *  compilation  ) 
Indicate that we have finished modifying a compilation. Required before calling ANeuralNetworksExecution_create.
An application is responsible to make sure that no other thread uses the compilation at the same time.
This function must only be called once for a given compilation.
See ANeuralNetworksCompilation for information on multithreaded usage.
 Parameters

compilation The compilation to be finished.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksCompilation_free()
void ANeuralNetworksCompilation_free  (  ANeuralNetworksCompilation *  compilation  ) 
Destroy a compilation.
The compilation need not have been finished by a call to ANeuralNetworksModel_finish.
See ANeuralNetworksCompilation for information on multithreaded usage.
 Parameters

compilation The compilation to be destroyed. Passing NULL is acceptable and results in no operation.
◆ ANeuralNetworksCompilation_setPreference()
int ANeuralNetworksCompilation_setPreference  (  ANeuralNetworksCompilation *  compilation, 
int32_t  preference  
) 
Sets the execution preference.
Provides guidance to the runtime when tradeoffs are possible.
See ANeuralNetworksCompilation for information on multithreaded usage.
 Parameters

compilation The compilation to be modified. preference Either PREFER_LOW_POWER, PREFER_SINGLE_FAST_ANSWER, or PREFER_SUSTAINED_SPEED.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksEvent_free()
void ANeuralNetworksEvent_free  (  ANeuralNetworksEvent *  event  ) 
Destroys the event.
See ANeuralNetworksExecution for information on multithreaded usage.
◆ ANeuralNetworksEvent_wait()
int ANeuralNetworksEvent_wait  (  ANeuralNetworksEvent *  event  ) 
Waits until the execution completes.
More than one thread can wait on an event. When the execution completes, all threads will be released.
See ANeuralNetworksExecution for information on multithreaded usage.
 Returns
 ANEURALNETWORKS_NO_ERROR if the execution completed normally.
◆ ANeuralNetworksExecution_create()
int ANeuralNetworksExecution_create  (  ANeuralNetworksCompilation *  compilation, 
ANeuralNetworksExecution **  execution  
) 
Create a ANeuralNetworksExecution to apply the given compilation. This only creates the object. Computation is only performed once ANeuralNetworksExecution_startCompute is invoked.
The provided compilation must outlive the execution.
See ANeuralNetworksExecution for information on multithreaded usage.
 Parameters

compilation The ANeuralNetworksCompilation to be evaluated. execution The newly created object or NULL if unsuccessful.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful, ANEURALNETWORKS_BAD_DATA if the compilation is invalid.
◆ ANeuralNetworksExecution_free()
void ANeuralNetworksExecution_free  (  ANeuralNetworksExecution *  execution  ) 
Destroy an execution.
If called on an execution for which ANeuralNetworksExecution_startCompute has been called, the function will return immediately but will mark the execution to be deleted once the computation completes. The related ANeuralNetworksEvent will be signaled and the ANeuralNetworksEvent_wait will return ANEURALNETWORKS_ERROR_DELETED.
See ANeuralNetworksExecution for information on multithreaded usage.
 Parameters

execution The execution to be destroyed. Passing NULL is acceptable and results in no operation.
◆ ANeuralNetworksExecution_setInput()
int ANeuralNetworksExecution_setInput  (  ANeuralNetworksExecution *  execution, 
int32_t  index,  
const ANeuralNetworksOperandType *  type,  
const void *  buffer,  
size_t  length  
) 
Associate a user buffer with an input of the model of the ANeuralNetworksExecution.
The provided buffer must outlive the execution.
If the input is optional, you can indicate that it is omitted by passing nullptr for buffer and 0 for length.
See ANeuralNetworksExecution for information on multithreaded usage.
 Parameters

execution The execution to be modified. index The index of the input argument we are setting. It is an index into the lists passed to ANeuralNetworksModel_identifyInputsAndOutputs. It is not the index associated with ANeuralNetworksModel_addOperand. type The type of the operand. This should be used to specify the dimensions that were set to 0 when the operand was added to the model. All other properties of the type must be the same as specified in the model. If the type is the same as specified when the model was built, NULL can be passed. buffer The buffer containing the data. length The length in bytes of the buffer.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful, ANEURALNETWORKS_BAD_DATA if the name is not recognized or the buffer is too small for the input.
◆ ANeuralNetworksExecution_setInputFromMemory()
int ANeuralNetworksExecution_setInputFromMemory  (  ANeuralNetworksExecution *  execution, 
int32_t  index,  
const ANeuralNetworksOperandType *  type,  
const ANeuralNetworksMemory *  memory,  
size_t  offset,  
size_t  length  
) 
Associate part of a memory object with an input of the model of the ANeuralNetworksExecution.
The provided memory must outlive the execution.
If the input is optional, you can indicate that it is omitted by using ANeuralNetworks_setInput instead, passing nullptr for buffer and 0 for length.
See ANeuralNetworksExecution for information on multithreaded usage.
 Parameters

execution The execution to be modified. index The index of the input argument we are setting. It is an index into the lists passed to ANeuralNetworksModel_identifyInputsAndOutputs. It is not the index associated with ANeuralNetworksModel_addOperand. type The type of the operand. This can be used to specify the dimensions that were set to 0 when the operand was added to the model. All other values must be the same as specified in the model. If the type is the same as specified when the model was built, NULL can be passed. memory The memory containing the data. offset This specifies the location of the data whithin the memory. The offset is in bytes from the start of memory. length The size in bytes of the data value.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful, ANEURALNETWORKS_BAD_DATA if the name is not recognized or the buffer is too small for the input.
◆ ANeuralNetworksExecution_setOutput()
int ANeuralNetworksExecution_setOutput  (  ANeuralNetworksExecution *  execution, 
int32_t  index,  
const ANeuralNetworksOperandType *  type,  
void *  buffer,  
size_t  length  
) 
Associate a user buffer with an output of the model of the ANeuralNetworksExecution.
If the output is optional, you can indicate that it is omitted by passing nullptr for buffer and 0 for length.
The provided buffer must outlive the execution.
See ANeuralNetworksExecution for information on multithreaded usage.
 Parameters

execution The execution to be modified. index The index of the output argument we are setting. It is an index into the lists passed to ANeuralNetworksModel_identifyInputsAndOutputs. It is not the index associated with ANeuralNetworksModel_addOperand. type The type of the operand. This can be used to specify the dimensions that were set to 0 when the operand was added to the model. All other values must be the same as specified in the model. If the type is the same as specified when the model was built, NULL can be passed. buffer The buffer where the data is to be written. length The length in bytes of the buffer.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful, ANEURALNETWORKS_BAD_DATA if the name is not recognized or the buffer is too small for the output.
◆ ANeuralNetworksExecution_setOutputFromMemory()
int ANeuralNetworksExecution_setOutputFromMemory  (  ANeuralNetworksExecution *  execution, 
int32_t  index,  
const ANeuralNetworksOperandType *  type,  
const ANeuralNetworksMemory *  memory,  
size_t  offset,  
size_t  length  
) 
Associate part of a memory object with an output of the model of the ANeuralNetworksExecution.
If the output is optional, you can indicate that it is omitted by using ANeuralNetworks_setOutput instead, passing nullptr for buffer and 0 for length.
The provided memory must outlive the execution.
See ANeuralNetworksExecution for information on multithreaded usage.
 Parameters

execution The execution to be modified. index The index of the output argument we are setting. It is an index into the lists passed to ANeuralNetworksModel_identifyInputsAndOutputs. It is not the index associated with ANeuralNetworksModel_addOperand. type The type of the operand. This can be used to specify the dimensions that were set to 0 when the operand was added to the model. All other values must be the same as specified in the model. If the type is the same as specified when the model was built, NULL can be passed. memory The memory where the data is to be stored. offset This specifies the location of the data whithin the memory. The offset is in bytes from the start of memory. length The length in bytes of the data value.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful, ANEURALNETWORKS_BAD_DATA if the name is not recognized or the buffer is too small for the output.
◆ ANeuralNetworksExecution_startCompute()
int ANeuralNetworksExecution_startCompute  (  ANeuralNetworksExecution *  execution, 
ANeuralNetworksEvent **  event  
) 
Schedule evaluation of the execution.
Schedules evaluation of the execution. Once the model has been applied and the outputs are ready to be consumed, the returned event will be signaled. Use ANeuralNetworksEvent_wait to wait for that event.
Multiple executions can be scheduled and evaluated concurrently. The runtime makes no guarantee on the ordering of completion of executions. If it's important to the application, the application should enforce the ordering by using ANeuralNetworksEvent_wait.
ANeuralNetworksEvent_wait must be called to recuperate the resources used by the execution.
See ANeuralNetworksExecution for information on multithreaded usage.
 Parameters

execution The execution to be scheduled and executed. event The event that will be signaled on completion. event is set to NULL if there's an error.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksMemory_createFromFd()
int ANeuralNetworksMemory_createFromFd  (  size_t  size, 
int  protect,  
int  fd,  
size_t  offset,  
ANeuralNetworksMemory **  memory  
) 
Creates a shared memory object from a file descriptor.
The shared memory is backed by a file descriptor via mmap. See ANeuralNetworksMemory for a description on how to use this shared memory.
 Parameters

size The requested size in bytes. Must not be larger than the file size. prot The desired memory protection for the mapping. It is either PROT_NONE or the bitwise OR of one or more of the following flags: PROT_READ, PROT_WRITE. fd The requested file descriptor. The file descriptor has to be mmapable. The file descriptor will be duplicated. offset The offset to the beginning of the file of the area to map. The offset has to be aligned to a page size. memory The memory object to be created. Set to NULL if unsuccessful.
 Returns
 ANEURALNETWORKS_NO_ERROR if the request completed normally.
◆ ANeuralNetworksMemory_free()
void ANeuralNetworksMemory_free  (  ANeuralNetworksMemory *  memory  ) 
Delete a memory object.
Destroys the object used by the run time to keep track of the memory. This will free the underlying actual memory if no other code has open handles to this memory.
 Parameters

memory The memory object to be freed.
◆ ANeuralNetworksModel_addOperand()
int ANeuralNetworksModel_addOperand  (  ANeuralNetworksModel *  model, 
const ANeuralNetworksOperandType *  type  
) 
Add an operand to a model.
The order in which the operands are added is important. The first one added to a model will have the index value 0, the second 1, etc. These indexes are used as operand identifiers in ANeuralNetworksModel_addOperation, ANeuralNetworksExecution_setInput, ANeuralNetworksExecution_setInputFromMemory, ANeuralNetworksExecution_setOutput, ANeuralNetworksExecution_setOutputFromMemory and ANeuralNetworksExecution_setOperandValue.
To build a model that can accomodate inputs of various sizes, as you may want to do for a CNN, set the size of the dimensions that will vary at run time to 0. If you do so, provide the full dimensions when calling ANeuralNetworksExecution_setInput or ANeuralNetworksExecution_setInputFromMemory.
Attempting to modify a model once ANeuralNetworksModel_finish has been called will return an error.
See ANeuralNetworksModel for information on multithreaded usage.
 Parameters

model The model to be modified. type The ANeuralNetworksOperandType that describes the shape of the operand.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksModel_addOperation()
int ANeuralNetworksModel_addOperation  (  ANeuralNetworksModel *  model, 
ANeuralNetworksOperationType  type,  
uint32_t  inputCount,  
const uint32_t *  inputs,  
uint32_t  outputCount,  
const uint32_t *  outputs  
) 
Add an operation to a model.
 Parameters

model The model to be modified. type The type of the operation. inputCount The number of entries in the inputs array. inputs An array of indexes identifying each operand. outputCount The number of entries in the outputs array. outputs An array of indexes identifying each operand.
The operands specified by inputs and outputs must have been previously added by calls to ANeuralNetworksModel_addOperand.
Attempting to modify a model once ANeuralNetworksModel_finish has been called will return an error.
See ANeuralNetworksModel for information on multithreaded usage.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksModel_create()
int ANeuralNetworksModel_create  (  ANeuralNetworksModel **  model  ) 
Create an empty ANeuralNetworksModel.
This only creates the object. Computation is performed once ANeuralNetworksExecution_startCompute is invoked.
The model should be constructed with calls to ANeuralNetworksModel_addOperation and ANeuralNetworksModel_addOperand
ANeuralNetworksModel_finish should be called once the model has been fully constructed.
ANeuralNetworksModel_free should be called once the model is no longer needed.
 Parameters

model The ANeuralNetworksModel to be created. Set to NULL if unsuccessful.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksModel_finish()
int ANeuralNetworksModel_finish  (  ANeuralNetworksModel *  model  ) 
Indicate that we have finished modifying a model. Required before calling ANeuralNetworksCompilation_create.
An application is responsible to make sure that no other thread uses the model at the same time.
This function must only be called once for a given model.
See ANeuralNetworksModel for information on multithreaded usage.
 Parameters

model The model to be finished.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksModel_free()
void ANeuralNetworksModel_free  (  ANeuralNetworksModel *  model  ) 
Destroy a model.
The model need not have been finished by a call to ANeuralNetworksModel_finish.
See ANeuralNetworksModel for information on multithreaded usage.
 Parameters

model The model to be destroyed. Passing NULL is acceptable and results in no operation.
◆ ANeuralNetworksModel_identifyInputsAndOutputs()
int ANeuralNetworksModel_identifyInputsAndOutputs  (  ANeuralNetworksModel *  model, 
uint32_t  inputCount,  
const uint32_t *  inputs,  
uint32_t  outputCount,  
const uint32_t *  outputs  
) 
Specfifies which operands will be the model's inputs and outputs.
An operand cannot be used for both input and output. Doing so will return an error.
 Parameters

model The model to be modified. inputCount The number of entries in the inputs array. inputs An array of indexes identifying the input operands. outputCount The number of entries in the outputs array. outputs An array of indexes identifying the output operands.
The operands specified by inputs and outputs must have been previously added by calls to ANeuralNetworksModel_addOperand.
Attempting to modify a model once ANeuralNetworksModel_finish has been called will return an error.
See ANeuralNetworksModel for information on multithreaded usage.
◆ ANeuralNetworksModel_relaxComputationFloat32toFloat16()
int ANeuralNetworksModel_relaxComputationFloat32toFloat16  (  ANeuralNetworksModel *  model, 
bool  allow  
) 
Specifies whether ANEURALNETWORKS_TENSOR_FLOAT32 is allowed to be calculated with range and/or precision as low as that of the IEEE 754 16bit floatingpoint format. By default, ANEURALNETWORKS_TENSOR_FLOAT32 must be calculated using at least the range and precision of the IEEE 754 32bit floatingpoint format.
 Parameters

model The model to be modified. allow 'true' indicates ANEURALNETWORKS_TENSOR_FLOAT32 may be calculated with range and/or precision as low as that of the IEEE 754 16bit floating point format. 'false' indicates ANEURALNETWORKS_TENSOR_FLOAT32 must be calculated using at least the range and precision of the IEEE 754 32bit floating point format.
Attempting to modify a model once ANeuralNetworksModel_finish has been called will return an error.
See ANeuralNetworksModel for information on multithreaded usage.
◆ ANeuralNetworksModel_setOperandValue()
int ANeuralNetworksModel_setOperandValue  (  ANeuralNetworksModel *  model, 
int32_t  index,  
const void *  buffer,  
size_t  length  
) 
Sets an operand to a constant value.
Values of length smaller or equal to ANEURALNETWORKS_MAX_SIZE_OF_IMMEDIATELY_COPIED_VALUES are immediately copied into the model.
For values of length greater than ANEURALNETWORKS_MAX_SIZE_OF_IMMEDIATELY_COPIED_VALUES, a pointer to the buffer is stored within the model. The application is responsible for not changing the content of this region until all executions using this model have completed. As the data may be copied during processing, modifying the data after this call yields undefined results.
For large tensors, using ANeuralNetworksModel_setOperandValueFromMemory is likely to be more efficient.
To indicate that an optional operand should be considered missing, pass nullptr for buffer and 0 for length.
Attempting to modify a model once ANeuralNetworksModel_finish has been called will return an error.
See ANeuralNetworksModel for information on multithreaded usage.
 Parameters

model The model to be modified. index The index of the model operand we're setting. buffer A pointer to the data to use. length The size in bytes of the data value.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.
◆ ANeuralNetworksModel_setOperandValueFromMemory()
int ANeuralNetworksModel_setOperandValueFromMemory  (  ANeuralNetworksModel *  model, 
int32_t  index,  
const ANeuralNetworksMemory *  memory,  
size_t  offset,  
size_t  length  
) 
Sets an operand to a value stored in a memory object.
The content of the memory is not copied. A reference to that memory is stored inside the model. The application is responsible for not changing the content of the memory region until all executions using this model have completed. As the data may be copied during processing, modifying the data after this call yields undefined results.
To indicate that an optional operand should be considered missing, use ANeuralNetworksModel_setOperandValue instead, passing nullptr for buffer.
Attempting to modify a model once ANeuralNetworksModel_finish has been called will return an error.
See ANeuralNetworksModel for information on multithreaded usage.
 Parameters

model The model to be modified. index The index of the model operand we're setting. buffer A pointer to the data to use. memory The memory containing the data. offset This specifies the location of the data within the memory. The offset is in bytes from the start of memory. length The size in bytes of the data value.
 Returns
 ANEURALNETWORKS_NO_ERROR if successful.