public static class
GpuDelegate.Options
This class is deprecated.
Use GpuDelegateFactory.Options instead.
Inherits from GpuDelegateFactory.Options for compatibility with existing code.
Inherited Constants
From class
org.tensorflow.lite.gpu.GpuDelegateFactory.Options
| int | INFERENCE_PREFERENCE_FAST_SINGLE_ANSWER | Delegate will be used only once, therefore, bootstrap/init time should be taken into account. |
| int | INFERENCE_PREFERENCE_SUSTAINED_SPEED | Prefer maximizing the throughput. |
Public Constructors
|
Options()
|
Inherited Methods
From class
org.tensorflow.lite.gpu.GpuDelegateFactory.Options
| boolean | |
| GpuDelegateFactory.Options.GpuBackend | |
| int | |
| String | |
| String | |
| boolean | |
| GpuDelegateFactory.Options | |
| GpuDelegateFactory.Options |
setInferencePreference(int preference)
Sets the inference preference for precision/compilation/runtime tradeoffs.
|
| GpuDelegateFactory.Options |
setPrecisionLossAllowed(boolean precisionLossAllowed)
Sets whether precision loss is allowed.
|
| GpuDelegateFactory.Options |
setQuantizedModelsAllowed(boolean quantizedModelsAllowed)
Enables running quantized models with the delegate.
|
| GpuDelegateFactory.Options |
setSerializationParams(String serializationDir, String modelToken)
Enables serialization on the delegate.
|