commit | c8e00eb6000ad1a31e3d0707ef48633f0013e640 | [log] [tgz] |
---|---|---|
author | Marat Dukhan <maratek@google.com> | Fri Oct 04 14:55:26 2019 -0700 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Fri Oct 04 14:55:49 2019 -0700 |
tree | 3f2ff94c944f01911d81d80004aed17ad488eda1 | |
parent | 12f1dea2655f61396dfb5f85be7228fc7ad22545 [diff] |
Disable logging in optimized builds, limit logging in fastbuild Reduce size_test: - 150K->140K on WAsm - 214K->187K on Android ARM64 - 207K->186K on Android ARMv7 PiperOrigin-RevId: 272963698
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.