Crate nnapi_sys

FFI Rust bindings for the Android Neural Networks API.

Structs

AHardwareBuffer

ANeuralNetworksBurst

ANeuralNetworksCompilation

ANeuralNetworksDevice

ANeuralNetworksEvent

ANeuralNetworksExecution

ANeuralNetworksMemory

ANeuralNetworksMemoryDesc

ANeuralNetworksModel

ANeuralNetworksOperandType

ANeuralNetworksOperandType describes the type of an operand.

ANeuralNetworksSymmPerChannelQuantParams

Parameters for ANEURALNETWORKS_TENSOR_QUANT8_SYMM_PER_CHANNEL operand.

__darwin_pthread_handler_rec

_opaque_pthread_attr_t

_opaque_pthread_cond_t

_opaque_pthread_condattr_t

_opaque_pthread_mutex_t

_opaque_pthread_mutexattr_t

_opaque_pthread_once_t

_opaque_pthread_rwlock_t

_opaque_pthread_rwlockattr_t

_opaque_pthread_t

Enums

OperandCode

Operand types.

OperationCode

Operation types.

ResultCode

Result codes.

Constants

ANEURALNETWORKS_BYTE_SIZE_OF_CACHE_TOKEN

ANEURALNETWORKS_DEVICE_ACCELERATOR

Dedicated accelerator for Machine Learning workloads.

ANEURALNETWORKS_DEVICE_CPU

The device runs NNAPI models on single or multi-core CPU.

ANEURALNETWORKS_DEVICE_GPU

The device can run NNAPI models and also accelerate graphics APIs such as OpenGL ES and Vulkan.

ANEURALNETWORKS_DEVICE_OTHER

The device does not fall into any category below.

ANEURALNETWORKS_DEVICE_UNKNOWN

The device type cannot be provided.

ANEURALNETWORKS_FUSED_NONE

NO fused activation function.

ANEURALNETWORKS_FUSED_RELU

Fused ReLU activation function.

ANEURALNETWORKS_FUSED_RELU1

Fused ReLU1 activation function.

ANEURALNETWORKS_FUSED_RELU6

Fused ReLU6 activation function.

ANEURALNETWORKS_MAX_SIZE_OF_IMMEDIATELY_COPIED_VALUES

ANEURALNETWORKS_PADDING_SAME

SAME padding. Padding on both ends are the “same”: padding_to_beginning = total_padding / 2 padding_to_end = (total_padding + 1)/2. i.e., for even number of padding, padding to both ends are exactly the same; for odd number of padding, padding to the ending is bigger than the padding to the beginning by 1.

ANEURALNETWORKS_PADDING_VALID

VALID padding. No padding. When the input size is not evenly divisible by the filter size, the input at the end that could not fill the whole filter tile will simply be ignored.

ANEURALNETWORKS_PREFER_FAST_SINGLE_ANSWER

Prefer returning a single answer as fast as possible, even if this causes more power consumption.

ANEURALNETWORKS_PREFER_LOW_POWER

Prefer executing in a way that minimizes battery drain. This is desirable for compilations that will be executed often.

ANEURALNETWORKS_PREFER_SUSTAINED_SPEED

Prefer maximizing the throughput of successive frames, for example when processing successive frames coming from the camera.

DurationCode_ANEURALNETWORKS_DURATION_IN_DRIVER

DurationCode_ANEURALNETWORKS_DURATION_ON_HARDWARE

DurationCode_ANEURALNETWORKS_FENCED_DURATION_IN_DRIVER

DurationCode_ANEURALNETWORKS_FENCED_DURATION_ON_HARDWARE

INT8_MAX

INT8_MIN

INT16_MAX

INT16_MIN

INT32_MAX

INT32_MIN

INT64_MAX

INT64_MIN

INTPTR_MAX

INTPTR_MIN

INT_FAST8_MAX

INT_FAST8_MIN

INT_FAST16_MAX

INT_FAST16_MIN

INT_FAST32_MAX

INT_FAST32_MIN

INT_FAST64_MAX

INT_FAST64_MIN

INT_LEAST8_MAX

INT_LEAST8_MIN

INT_LEAST16_MAX

INT_LEAST16_MIN

INT_LEAST32_MAX

INT_LEAST32_MIN

INT_LEAST64_MAX

INT_LEAST64_MIN

PriorityCode_ANEURALNETWORKS_PRIORITY_DEFAULT

PriorityCode_ANEURALNETWORKS_PRIORITY_HIGH

PriorityCode_ANEURALNETWORKS_PRIORITY_LOW

PriorityCode_ANEURALNETWORKS_PRIORITY_MEDIUM

RSIZE_MAX

SIG_ATOMIC_MAX

SIG_ATOMIC_MIN

SIZE_MAX

UINT8_MAX

UINT16_MAX

UINT32_MAX

UINT64_MAX

UINTPTR_MAX

UINT_FAST8_MAX

UINT_FAST16_MAX

UINT_FAST32_MAX

UINT_FAST64_MAX

UINT_LEAST8_MAX

UINT_LEAST16_MAX

UINT_LEAST32_MAX

UINT_LEAST64_MAX

WINT_MAX

WINT_MIN

_DARWIN_FEATURE_64_BIT_INODE

_DARWIN_FEATURE_ONLY_64_BIT_INODE

_DARWIN_FEATURE_ONLY_UNIX_CONFORMANCE

_DARWIN_FEATURE_ONLY_VERS_1050

_DARWIN_FEATURE_UNIX_CONFORMANCE

__DARWIN_64_BIT_INO_T

__DARWIN_C_ANSI

__DARWIN_C_FULL

__DARWIN_C_LEVEL

__DARWIN_NON_CANCELABLE

__DARWIN_NO_LONG_LONG

__DARWIN_ONLY_64_BIT_INO_T

__DARWIN_ONLY_UNIX_CONFORMANCE

__DARWIN_ONLY_VERS_1050

__DARWIN_SUF_EXTSN

__DARWIN_UNIX03

__DARWIN_VERS_1050

__PTHREAD_ATTR_SIZE__

__PTHREAD_CONDATTR_SIZE__

__PTHREAD_COND_SIZE__

__PTHREAD_MUTEXATTR_SIZE__

__PTHREAD_MUTEX_SIZE__

__PTHREAD_ONCE_SIZE__

__PTHREAD_RWLOCKATTR_SIZE__

__PTHREAD_RWLOCK_SIZE__

__PTHREAD_SIZE__

__STDC_WANT_LIB_EXT1__

__WORDSIZE

__bool_true_false_are_defined

__has_ptrcheck

false_

true_

Functions

ANeuralNetworksBurst_create^⚠

Create a {@link ANeuralNetworksBurst} to apply the given compilation. This only creates the burst object. Computation is only performed once {@link ANeuralNetworksExecution_burstCompute} is invoked with a valid {@link ANeuralNetworksExecution} and {@link ANeuralNetworksBurst}.

ANeuralNetworksBurst_free^⚠

Destroys the burst object.

ANeuralNetworksCompilation_create^⚠

Create a {@link ANeuralNetworksCompilation} to compile the given model.

ANeuralNetworksCompilation_createForDevices^⚠

Create a {@link ANeuralNetworksCompilation} to compile the given model for a specified set of devices. If more than one device is specified, the compilation will distribute the workload automatically across the devices. The model must be fully supported by the specified set of devices. This means that ANeuralNetworksModel_getSupportedOperationsForDevices() must have returned true for every operation for that model/devices pair.

ANeuralNetworksCompilation_finish^⚠

Indicate that we have finished modifying a compilation. Required before calling {@link ANeuralNetworksBurst_create} or {@link ANeuralNetworksExecution_create}.

ANeuralNetworksCompilation_free^⚠

Destroy a compilation.

ANeuralNetworksCompilation_setCaching^⚠

Sets the compilation caching signature and the cache directory.

ANeuralNetworksCompilation_setPreference^⚠

Sets the execution preference.

ANeuralNetworksCompilation_setPriority^⚠

Set the execution priority.

ANeuralNetworksCompilation_setTimeout^⚠

Set the maximum expected duration for compiling the model.

ANeuralNetworksDevice_getFeatureLevel^⚠

Get the supported NNAPI version of the specified device.

ANeuralNetworksDevice_getName^⚠

Get the name of the specified device.

ANeuralNetworksDevice_getType^⚠

Get the type of a given device.

ANeuralNetworksDevice_getVersion^⚠

Get the version of the driver implementation of the specified device.

ANeuralNetworksDevice_wait^⚠

Wait until the device is in a live state.

ANeuralNetworksEvent_createFromSyncFenceFd^⚠

Create a {@link ANeuralNetworksEvent} from a sync_fence file descriptor.

ANeuralNetworksEvent_free^⚠

Destroys the event.

ANeuralNetworksEvent_getSyncFenceFd^⚠

Get sync_fence file descriptor from the event.

ANeuralNetworksEvent_wait^⚠

Waits until the execution completes.

ANeuralNetworksExecution_burstCompute^⚠

Schedule synchronous evaluation of the execution on a burst object.

ANeuralNetworksExecution_compute^⚠

Schedule synchronous evaluation of the execution.

ANeuralNetworksExecution_create^⚠

Create a {@link ANeuralNetworksExecution} to apply the given compilation. This only creates the object. Computation is only performed once {@link ANeuralNetworksExecution_burstCompute}, {@link ANeuralNetworksExecution_compute}, {@link ANeuralNetworksExecution_startCompute} or {@link ANeuralNetworksExecution_startComputeWithDependencies} is invoked.

ANeuralNetworksExecution_free^⚠

Destroy an execution.

ANeuralNetworksExecution_getDuration^⚠

Get the time spent in the specified {@link ANeuralNetworksExecution}, in nanoseconds.

ANeuralNetworksExecution_getOutputOperandDimensions^⚠

Get the dimensional information of the specified output operand of the model of the {@link ANeuralNetworksExecution}. The target output operand cannot be a scalar.

ANeuralNetworksExecution_getOutputOperandRank^⚠

Get the dimensional information of the specified output operand of the model of the {@link ANeuralNetworksExecution}.

ANeuralNetworksExecution_setInput^⚠

Associate a user buffer with an input of the model of the {@link ANeuralNetworksExecution}. Evaluation of the execution must not have been scheduled. Once evaluation of the execution has been scheduled, the application must not change the content of the buffer until the execution has completed. Evaluation of the execution will not change the content of the buffer.

ANeuralNetworksExecution_setInputFromMemory^⚠

Associate a region of a memory object with an input of the model of the {@link ANeuralNetworksExecution}. Evaluation of the execution must not have been scheduled. Once evaluation of the execution has been scheduled, the application must not change the content of the region until the execution has completed. Evaluation of the execution will not change the content of the region.

ANeuralNetworksExecution_setLoopTimeout^⚠

Set the maximum duration of WHILE loops in the specified execution.

ANeuralNetworksExecution_setMeasureTiming^⚠

Specifies whether duration of the {@link ANeuralNetworksExecution} is to be measured. Evaluation of the execution must not have been scheduled.

ANeuralNetworksExecution_setOutput^⚠

Associate a user buffer with an output of the model of the {@link ANeuralNetworksExecution}. Evaluation of the execution must not have been scheduled. Once evaluation of the execution has been scheduled, the application must not change the content of the buffer until the execution has completed.

ANeuralNetworksExecution_setOutputFromMemory^⚠

Associate a region of a memory object with an output of the model of the {@link ANeuralNetworksExecution}. Evaluation of the execution must not have been scheduled. Once evaluation of the execution has been scheduled, the application must not change the content of the region until the execution has completed.

ANeuralNetworksExecution_setTimeout^⚠

Set the maximum expected duration of the specified execution.

ANeuralNetworksExecution_startCompute^⚠

Schedule asynchronous evaluation of the execution.

ANeuralNetworksExecution_startComputeWithDependencies^⚠

Schedule asynchronous evaluation of the execution with dependencies.

ANeuralNetworksMemoryDesc_addInputRole^⚠

Specify that a memory object will be playing the role of an input to an execution created from a particular compilation.

ANeuralNetworksMemoryDesc_addOutputRole^⚠

Specify that a memory object will be playing the role of an output to an execution created from a particular compilation.

ANeuralNetworksMemoryDesc_create^⚠

Create a {@link ANeuralNetworksMemoryDesc} with no properties.

ANeuralNetworksMemoryDesc_finish^⚠

Indicate that we have finished modifying a memory descriptor. Required before calling {@link ANeuralNetworksMemory_createFromDesc}.

ANeuralNetworksMemoryDesc_free^⚠

Destroy a memory descriptor.

ANeuralNetworksMemoryDesc_setDimensions^⚠

Set the dimensional information of the memory descriptor.

ANeuralNetworksMemory_copy^⚠

Copies data from one memory object to another.

ANeuralNetworksMemory_createFromAHardwareBuffer^⚠

Creates a shared memory object from an AHardwareBuffer handle.

ANeuralNetworksMemory_createFromDesc^⚠

Creates a memory object from a memory descriptor.

ANeuralNetworksMemory_createFromFd^⚠

Creates a shared memory object from a file descriptor.

ANeuralNetworksMemory_free^⚠

Delete a memory object.

ANeuralNetworksModel_addOperand^⚠

Add an operand to a model.

ANeuralNetworksModel_addOperation^⚠

Add an operation to a model.

ANeuralNetworksModel_create^⚠

Create an empty {@link ANeuralNetworksModel}.

ANeuralNetworksModel_finish^⚠

Indicate that we have finished modifying a model. Required before calling {@link ANeuralNetworksCompilation_create} and {@link ANeuralNetworksCompilation_createForDevices}.

ANeuralNetworksModel_free^⚠

Destroy a model.

ANeuralNetworksModel_getSupportedOperationsForDevices^⚠

Get the supported operations for a specified set of devices. If multiple devices are selected, the supported operation list is a union of supported operations of all selected devices.

ANeuralNetworksModel_identifyInputsAndOutputs^⚠

Specifies which operands will be the model’s inputs and outputs. Every model must have at least one input and one output.

ANeuralNetworksModel_relaxComputationFloat32toFloat16^⚠

Specifies whether {@link ANEURALNETWORKS_TENSOR_FLOAT32} is allowed to be calculated with range and/or precision as low as that of the IEEE 754 16-bit floating-point format. By default, {@link ANEURALNETWORKS_TENSOR_FLOAT32} must be calculated using at least the range and precision of the IEEE 754 32-bit floating-point format.

ANeuralNetworksModel_setOperandSymmPerChannelQuantParams^⚠

Sets an operand’s per channel quantization parameters.

ANeuralNetworksModel_setOperandValue^⚠

Sets an operand to a constant value.

ANeuralNetworksModel_setOperandValueFromMemory^⚠

Sets an operand to a value stored in a memory object.

ANeuralNetworksModel_setOperandValueFromModel^⚠

Sets an operand to a value that is a reference to another NNAPI model.

ANeuralNetworks_getDefaultLoopTimeout^⚠

Get the default timeout value for WHILE loops.

ANeuralNetworks_getDevice^⚠

Get the representation of the specified device.

ANeuralNetworks_getDeviceCount^⚠

Get the number of available devices.

ANeuralNetworks_getMaximumLoopTimeout^⚠

Get the maximum timeout value for WHILE loops.

ANeuralNetworks_getRuntimeFeatureLevel^⚠

Type Aliases

ANeuralNetworksOperationType

DeviceTypeCode

Device types.

DurationCode

Different duration measurements.

FuseCode

Fused activation function types.

PaddingCode

Implicit padding algorithms.

PreferenceCode

Execution preferences.

PriorityCode

Relative execution priority.

__builtin_va_list

__darwin_blkcnt_t

__darwin_blksize_t

__darwin_clock_t

__darwin_ct_rune_t

__darwin_dev_t

__darwin_fsblkcnt_t

__darwin_fsfilcnt_t

__darwin_gid_t

__darwin_id_t

__darwin_ino64_t

__darwin_ino_t

__darwin_intptr_t

__darwin_mach_port_name_t

__darwin_mach_port_t

__darwin_mbstate_t

__darwin_mode_t

__darwin_natural_t

__darwin_off_t

__darwin_pid_t

__darwin_pthread_attr_t

__darwin_pthread_cond_t

__darwin_pthread_condattr_t

__darwin_pthread_key_t

__darwin_pthread_mutex_t

__darwin_pthread_mutexattr_t

__darwin_pthread_once_t

__darwin_pthread_rwlock_t

__darwin_pthread_rwlockattr_t

__darwin_pthread_t

__darwin_ptrdiff_t

__darwin_rune_t

__darwin_sigset_t

__darwin_size_t

__darwin_socklen_t

__darwin_ssize_t

__darwin_suseconds_t

__darwin_time_t

__darwin_uid_t

__darwin_useconds_t

__darwin_uuid_string_t

__darwin_uuid_t

__darwin_va_list

__darwin_wchar_t

__darwin_wint_t

__int8_t

__int16_t

__int32_t

__int64_t

__uint8_t

__uint16_t

__uint32_t

__uint64_t

_bindgen_ty_1

For {@link ANeuralNetworksModel_setOperandValue}, values with a length smaller or equal to this will be immediately copied into the model. The size is in bytes.

_bindgen_ty_2

For {@link ANeuralNetworksCompilation_setCaching}, specify the size of the cache token required from the application. The size is in bytes.

int_fast8_t

int_fast16_t

int_fast32_t

int_fast64_t

int_least8_t

int_least16_t

int_least32_t

int_least64_t

intmax_t

max_align_t

register_t

syscall_arg_t

u_int8_t

u_int16_t

u_int32_t

u_int64_t

uint_fast8_t

uint_fast16_t

uint_fast32_t

uint_fast64_t

uint_least8_t

uint_least16_t

uint_least32_t

uint_least64_t

uintmax_t

user_addr_t

user_long_t

user_off_t

user_size_t

user_ssize_t

user_time_t

user_ulong_t

wchar_t

Unions

__mbstate_t