• Home
Name Date Size #Lines LOC

..--

sl/06-Sep-2024-2,006568

BUILDD06-Sep-20242.5 KiB10595

NeuralNetworksShim.hD06-Sep-202472.1 KiB1,780373

NeuralNetworksTypes.hD06-Sep-202434.5 KiB915451

README.mdD06-Sep-2024865 1612

nnapi_handler.ccD06-Sep-20245.6 KiB158117

nnapi_handler.hD06-Sep-202411.5 KiB345242

nnapi_handler_test.ccD06-Sep-202410.1 KiB231177

nnapi_implementation.ccD06-Sep-202424.7 KiB582475

nnapi_implementation.hD06-Sep-202488.1 KiB2,135244

nnapi_implementation_disabled.ccD06-Sep-20241.1 KiB3212

nnapi_implementation_test.ccD06-Sep-20247.6 KiB143123

nnapi_util.ccD06-Sep-20242.4 KiB8249

nnapi_util.hD06-Sep-20241.9 KiB4814

README.md

1# Android Neural Network API
2
3The Android Neural Networks API (NNAPI) is an Android C API designed for running
4computationally intensive operators for machine learning on mobile devices.
5Tensorflow Lite is designed to use the NNAPI to perform hardware-accelerated
6inference operators on supported devices.
7Based on the app’s requirements and the hardware capabilities on a device, the
8NNAPI can distribute the computation workload across available on-device
9processors, including dedicated neural network hardware, graphics processing
10units (GPUs), and digital signal processors (DSPs).
11For devices that lack a specialized vendor driver, the NNAPI runtime relies on
12optimized code to execute requests on the CPU. For more information about the
13NNAPI, please refer to the [NNAPI documentation](https://developer.android.com/ndk/guides/neuralnetworks/index.html)
14
15
16