An options class for controlling runtime interpreter behavior.
Options()
|
|
Options(InterpreterApi.Options options)
|
Interpreter.Options | |
Interpreter.Options |
addDelegateFactory(DelegateFactory delegateFactory)
Adds a
DelegateFactory which will be invoked to apply its created Delegate
during interpreter creation. |
Interpreter.Options |
setAllowBufferHandleOutput(boolean allow)
Advanced: Set if buffer handle output is allowed.
|
Interpreter.Options |
setAllowFp16PrecisionForFp32(boolean allow)
This method is deprecated. Prefer using NnApiDelegate.Options#setAllowFp16(boolean
enable).
|
Interpreter.Options |
setCancellable(boolean allow)
Advanced: Set if the interpreter is able to be cancelled.
|
Interpreter.Options |
setNumThreads(int numThreads)
Sets the number of threads to be used for ops that support multi-threading.
|
Interpreter.Options |
setRuntime(InterpreterApi.Options.TfLiteRuntime runtime)
Specify where to get the TF Lite runtime implementation from.
|
Interpreter.Options |
setUseNNAPI(boolean useNNAPI)
Sets whether to use NN API (if available) for op execution.
|
Interpreter.Options |
setUseXNNPACK(boolean useXNNPACK)
Enable or disable an optimized set of CPU kernels (provided by XNNPACK).
|
Adds a Delegate
to be applied during interpreter creation.
Delegates added here are applied before any delegates created from a DelegateFactory
that was added with addDelegateFactory(DelegateFactory)
.
Note that TF Lite in Google Play Services (see setRuntime(InterpreterApi.Options.TfLiteRuntime)
) does not support
external (developer-provided) delegates, and adding a Delegate
other than ERROR(/NnApiDelegate)
here is not allowed when using TF Lite in Google Play Services.
delegate |
---|
Adds a DelegateFactory
which will be invoked to apply its created Delegate
during interpreter creation.
Delegates from a delegated factory that was added here are applied after any delegates
added with addDelegate(Delegate)
.
delegateFactory |
---|
Advanced: Set if buffer handle output is allowed.
When a Delegate
supports hardware acceleration, the interpreter will make the data
of output tensors available in the CPU-allocated tensor buffers by default. If the client can
consume the buffer handle directly (e.g. reading output from OpenGL texture), it can set this
flag to false, avoiding the copy of data to the CPU buffer. The delegate documentation should
indicate whether this is supported and how it can be used.
WARNING: This is an experimental interface that is subject to change.
allow |
---|
This method is deprecated.
Prefer using NnApiDelegate.Options#setAllowFp16(boolean
enable).
Sets whether to allow float16 precision for FP32 calculation when possible. Defaults to false (disallow).
allow |
---|
Advanced: Set if the interpreter is able to be cancelled.
Interpreters may have an experimental API setCancelled(boolean).
If this interpreter is cancellable and such a method is invoked, a cancellation flag will be
set to true. The interpreter will check the flag between Op invocations, and if it's true
, the interpreter will stop execution. The interpreter will remain a cancelled state
until explicitly "uncancelled" by setCancelled(false)
.
allow |
---|
Sets the number of threads to be used for ops that support multi-threading.
numThreads
should be >= -1
. Setting numThreads
to 0 has the effect
of disabling multithreading, which is equivalent to setting numThreads
to 1. If
unspecified, or set to the value -1, the number of threads used will be
implementation-defined and platform-dependent.
numThreads |
---|
Specify where to get the TF Lite runtime implementation from.
runtime |
---|
Sets whether to use NN API (if available) for op execution. Defaults to false (disabled).
useNNAPI |
---|
Enable or disable an optimized set of CPU kernels (provided by XNNPACK). Enabled by default.
useXNNPACK |
---|