experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
mm-llvm-bazel
STT-tensorflow/tensorflow/lite/nnapi
History
A. Unique TensorFlower 976ed7aa4a Added dlerror() error message to log. 
This can provide more information when libneuralnetworks.so cannot be loaded successfully.

PiperOrigin-RevId: 336185850
Change-Id: I3cd03e2d96ff1eb216e89346f7e0186fd231cee5
2020-10-08 16:26:53 -07:00
..
BUILD Changes excluded by Copybara 2020-08-25 14:55:59 -07:00
NeuralNetworksShim.h Load the sync fence / dependency functions in the neuralnetworks shim layer 2020-07-06 14:44:30 -07:00
NeuralNetworksTypes.h add 1.3 NNAPI DurationCode. 2020-07-28 13:48:26 -07:00
nnapi_handler_test.cc
nnapi_handler.cc
nnapi_handler.h Add support for TENSOR_QUANT8_ASYMM_SIGNED in NNAPI delegate 2020-06-23 05:46:05 -07:00
nnapi_implementation_disabled.cc
nnapi_implementation_test.cc
nnapi_implementation.cc Added dlerror() error message to log. 2020-10-08 16:26:53 -07:00
nnapi_implementation.h Document the meaning of the return values for 2020-09-25 10:15:48 -07:00
nnapi_util.cc
nnapi_util.h
README.md

README.md

Android Neural Network API

The Android Neural Networks API (NNAPI) is an Android C API designed for running computationally intensive operators for machine learning on mobile devices. Tensorflow Lite is designed to use the NNAPI to perform hardware-accelerated inference operators on supported devices. Based on the app’s requirements and the hardware capabilities on a device, the NNAPI can distribute the computation workload across available on-device processors, including dedicated neural network hardware, graphics processing units (GPUs), and digital signal processors (DSPs). For devices that lack a specialized vendor driver, the NNAPI runtime relies on optimized code to execute requests on the CPU. For more information about the NNAPI, please refer to the NNAPI documentation