TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED constant - TfLiteGpuInferenceUsage class - native library

TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED constant

int const TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED

Prefer maximizing the throughput. Same delegate will be used repeatedly on multiple inputs.

Implementation

static const int TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED = 1;