Paket: libarmnn-cpuref-backend22 (20.08-9)
Links für libarmnn-cpuref-backend22
Debian-Ressourcen:
Quellcode-Paket armnn herunterladen:
Betreuer:
Ähnliche Pakete:
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 dynamically loadable Reference backend package.
Andere Pakete mit Bezug zu libarmnn-cpuref-backend22
|
|
|
|
-
- dep: libarmnn22 (= 20.08-9)
- Arm NN is an inference engine for CPUs, GPUs and NPUs
-
- dep: libarmnnaclcommon22 (= 20.08-9) [arm64, armhf]
- Arm NN is an inference engine for CPUs, GPUs and NPUs
-
- dep: libc6 (>= 2.27)
- GNU-C-Bibliothek: Laufzeitbibliotheken
auch ein virtuelles Paket, bereitgestellt durch libc6-udeb
-
- dep: libgcc-s1 (>= 3.0) [nicht armhf]
- GCC Support-Bibliothek
- dep: libgcc-s1 (>= 3.5) [armhf]
-
- dep: libstdc++6 (>= 5.2)
- GNU-Implementierung der Standard-C++-Bibliothek (Version 3)
libarmnn-cpuref-backend22 herunterladen
| Architektur | Paketgröße | Größe (installiert) | Dateien |
|---|---|---|---|
| amd64 | 181,1 kB | 919,0 kB | [Liste der Dateien] |
| arm64 | 161,2 kB | 899,0 kB | [Liste der Dateien] |
| armhf | 152,4 kB | 622,0 kB | [Liste der Dateien] |
| i386 | 188,6 kB | 917,0 kB | [Liste der Dateien] |
| mips64el | 151,4 kB | 1.347,0 kB | [Liste der Dateien] |
| mipsel | 149,1 kB | 1.028,0 kB | [Liste der Dateien] |
| ppc64el | 177,8 kB | 1.107,0 kB | [Liste der Dateien] |