commit | c068bb620f309a50c1b75b50c66441b9fe4ec359 | [log] [tgz] |
---|---|---|
author | Marat Dukhan <maratek@google.com> | Fri Oct 04 13:24:39 2019 -0700 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Fri Oct 04 13:25:02 2019 -0700 |
tree | ae6f9144d5919595211e7452a5f57ef413580a74 | |
parent | 4efb3517fd5b7ce3dc0a345e52ba798c2a5fcc38 [diff] |
End-to-end benchmarks on MobileNet v1 and MobileNet v2 models PiperOrigin-RevId: 272945172
XNNPACK is a highly optimized library of floating-point neural network inference operators for ARM, WebAssembly, and x86 (SSE2 level) platforms. XNNPACK is not intended for direct use by deep learning practitioners researchers; instead it provides low-level performance primitives for accelerating high-level machine learning frameworks, such as MediaPipe, TensorFlow Lite, and TensorFlow.js.
XNNPACK implements the following neural network operators:
All operators in XNNPACK support NHWC layout, but additionally allow custom stride along the Channel dimension. Thus, operators can consume a subset of channels in the input tensor, and produce a subset of channels in the output tensor, providing a zero-cost Channel Split and Channel Concatenation operations.
XNNPACK is a based on QNNPACK library. However, unlike QNNPACK, XNNPACK focuses entirely on floating-point operators, and its API is no longer compatible with QNNPACK.