Paket: libarmnn-dev (20.08-9)

[ Källkod: armnn  ]

Arm NN is an inference engine for CPUs, GPUs and NPUs

Arm NN is a set of tools that enables machine learning workloads on any hardware. It provides a bridge between existing neural network frameworks and whatever hardware is available and supported. On arm architectures (arm64 and armhf) it utilizes the Arm Compute Library to target Cortex-A CPUs, Mali GPUs and Ethos NPUs as efficiently as possible. On other architectures/hardware it falls back to unoptimised functions.

This release supports Caffe, TensorFlow, TensorFlow Lite, and ONNX. Arm NN takes networks from these frameworks, translates them to the internal Arm NN format and then through the Arm Compute Library, deploys them efficiently on Cortex-A CPUs, and, if present, Mali GPUs.

This is the development package containing header files.

Andra paket besläktade med libarmnn-dev

• dep: libarmnn22 (= 20.08-9)

  Arm NN is an inference engine for CPUs, GPUs and NPUs

Hämta libarmnn-dev

Hämtningar för alla tillgängliga arkitekturer

Arkitektur	Paketstorlek	Installerad storlek	Filer
amd64	45,0 kbyte	356,0 kbyte	[filförteckning]
arm64	45,0 kbyte	356,0 kbyte	[filförteckning]
armhf	45,0 kbyte	356,0 kbyte	[filförteckning]
i386	45,0 kbyte	356,0 kbyte	[filförteckning]
mips64el	45,0 kbyte	356,0 kbyte	[filförteckning]
mipsel	45,0 kbyte	356,0 kbyte	[filförteckning]
ppc64el	45,0 kbyte	356,0 kbyte	[filförteckning]