aurorafw.android.platform.neuralnetworks

Undocumented in source.

Members

Aliases

ANeuralNetworksOperationType alias ANeuralNetworksOperationType = int: @file aurorafw/android/platform/neuralnetworks.d

Enums

ANEURALNETWORKS_MAX_SIZE_OF_IMMEDIATELY_COPIED_VALUES anonymousenum ANEURALNETWORKS_MAX_SIZE_OF_IMMEDIATELY_COPIED_VALUES: 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.
FuseCode enum FuseCode: Fused activation function types.
OperandCode enum OperandCode: Operand types.
OperationCode enum OperationCode: Operation types.
PaddingCode enum PaddingCode: Implicit padding algorithms.
PreferenceCode enum PreferenceCode: Execution preferences.
ResultCode enum ResultCode: Result codes.

Functions

ANeuralNetworksCompilation_create
int ANeuralNetworksCompilation_create(ANeuralNetworksModel* model, ANeuralNetworksCompilation** compilation): Create a {@link ANeuralNetworksCompilation} to compile the given model.
ANeuralNetworksCompilation_finish int ANeuralNetworksCompilation_finish(ANeuralNetworksCompilation* compilation): Indicate that we have finished modifying a compilation. Required before calling {@link ANeuralNetworksExecution_create}.
ANeuralNetworksCompilation_free void ANeuralNetworksCompilation_free(ANeuralNetworksCompilation* compilation): Destroy a compilation.
ANeuralNetworksCompilation_setPreference int ANeuralNetworksCompilation_setPreference(ANeuralNetworksCompilation* compilation, int preference): Sets the execution preference.
ANeuralNetworksEvent_free void ANeuralNetworksEvent_free(ANeuralNetworksEvent* event): Destroys the event.
ANeuralNetworksEvent_wait int ANeuralNetworksEvent_wait(ANeuralNetworksEvent* event): Waits until the execution completes.
ANeuralNetworksExecution_create
int ANeuralNetworksExecution_create(ANeuralNetworksCompilation* compilation, ANeuralNetworksExecution** execution): Create a {@link ANeuralNetworksExecution} to apply the given compilation. This only creates the object. Computation is only performed once {@link ANeuralNetworksExecution_startCompute} is invoked.
ANeuralNetworksExecution_free void ANeuralNetworksExecution_free(ANeuralNetworksExecution* execution): Destroy an execution.
ANeuralNetworksExecution_setInput int ANeuralNetworksExecution_setInput(ANeuralNetworksExecution* execution, int index, const(ANeuralNetworksOperandType)* type, const(void)* buffer, size_t length): Associate a user buffer with an input of the model of the {@link ANeuralNetworksExecution}.
ANeuralNetworksExecution_setInputFromMemory int ANeuralNetworksExecution_setInputFromMemory(ANeuralNetworksExecution* execution, int 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 {@link ANeuralNetworksExecution}.
ANeuralNetworksExecution_setOutput int ANeuralNetworksExecution_setOutput(ANeuralNetworksExecution* execution, int index, const(ANeuralNetworksOperandType)* type, void* buffer, size_t length): Associate a user buffer with an output of the model of the {@link ANeuralNetworksExecution}.
ANeuralNetworksExecution_setOutputFromMemory int ANeuralNetworksExecution_setOutputFromMemory(ANeuralNetworksExecution* execution, int 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 {@link ANeuralNetworksExecution}.
ANeuralNetworksExecution_startCompute
int ANeuralNetworksExecution_startCompute(ANeuralNetworksExecution* execution, ANeuralNetworksEvent** event): Schedule evaluation of the execution.
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.
ANeuralNetworksMemory_free void ANeuralNetworksMemory_free(ANeuralNetworksMemory* memory): Delete a memory object.
ANeuralNetworksModel_addOperand int ANeuralNetworksModel_addOperand(ANeuralNetworksModel* model, const(ANeuralNetworksOperandType)* type): Add an operand to a model.
ANeuralNetworksModel_addOperation int ANeuralNetworksModel_addOperation(ANeuralNetworksModel* model, ANeuralNetworksOperationType type, uint inputCount, const(uint)* inputs, uint outputCount, const(uint)* outputs): Add an operation to a model.
ANeuralNetworksModel_create
int ANeuralNetworksModel_create(ANeuralNetworksModel** model): Create an empty {@link ANeuralNetworksModel}.
ANeuralNetworksModel_finish int ANeuralNetworksModel_finish(ANeuralNetworksModel* model): Indicate that we have finished modifying a model. Required before calling {@link ANeuralNetworksCompilation_create}.
ANeuralNetworksModel_free void ANeuralNetworksModel_free(ANeuralNetworksModel* model): Destroy a model.
ANeuralNetworksModel_identifyInputsAndOutputs int ANeuralNetworksModel_identifyInputsAndOutputs(ANeuralNetworksModel* model, uint inputCount, const(uint)* inputs, uint outputCount, const(uint)* outputs): Specifies which operands will be the model's inputs and outputs. Every model must have at least one input and one output.
ANeuralNetworksModel_relaxComputationFloat32toFloat16 int ANeuralNetworksModel_relaxComputationFloat32toFloat16(ANeuralNetworksModel* model, bool allow): 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_setOperandValue int ANeuralNetworksModel_setOperandValue(ANeuralNetworksModel* model, int index, const(void)* buffer, size_t length): Sets an operand to a constant value.
ANeuralNetworksModel_setOperandValueFromMemory int ANeuralNetworksModel_setOperandValueFromMemory(ANeuralNetworksModel* model, int index, const(ANeuralNetworksMemory)* memory, size_t offset, size_t length): Sets an operand to a value stored in a memory object.

Structs

ANeuralNetworksCompilation struct ANeuralNetworksCompilation: ANeuralNetworksCompilation is an opaque type that can be used to compile a machine learning model.
ANeuralNetworksEvent struct ANeuralNetworksEvent: ANeuralNetworksEvent is an opaque type that represents an event that will be signaled once an execution completes.
ANeuralNetworksExecution struct ANeuralNetworksExecution: ANeuralNetworksExecution is an opaque type that can be used to apply a machine learning model to a set of inputs.
ANeuralNetworksMemory struct ANeuralNetworksMemory: ANeuralNetworksMemory is an opaque type that represents memory.
ANeuralNetworksModel struct ANeuralNetworksModel: ANeuralNetworksModel is an opaque type that contains a description of the mathematical operations that constitute the model.
ANeuralNetworksOperandType struct ANeuralNetworksOperandType: ANeuralNetworksOperandType describes the type of an operand. This structure is used to describe both scalars and tensors.

aurorafw.android.platform.neuralnetworks

Members

Aliases

Enums

Functions

Structs

Meta

Source