Пакет: onnxruntime-tools (1.19.2+dfsg-9 и други)

[ Източник: onnxruntime  ]

cross-platform inference and training ML accelerator (tools)

ONNX Runtime is a performance-focused complete scoring engine for Open Neural Network Exchange (ONNX) models, with an open extensible architecture to continually address the latest developments in AI and Deep Learning. ONNX Runtime stays up to date with the ONNX standard with complete implementation of all ONNX operators, and supports all ONNX releases (1.2+) with both future and backwards compatibility. Please refer to this page for ONNX opset compatibility details.

This package provides the onnxruntime tools.

Други пакети, свързани с onnxruntime-tools

• dep: libc6 (>= 2.38) [x32]

  GNU C Library: Shared libraries
  също и виртуален пакет, предлаган от libc6-udeb

• dep: libcpuinfo0 (>= 0.0~git20220819.8ec7bd9) [x32]

  CPU INFOrmation library (shared object)

• dep: libgcc-s1 (>= 4.0) [x32]

  GCC support library

• dep: libonnx1t64 (>= 1.14.1) [x32]

  Open Neural Network Exchange (ONNX) (libs)

• dep: libprotobuf32t64 (>= 3.21.12) [x32]

  protocol buffers C++ library

• dep: libpthreadpool0 (>= 0.0~git20200423.6acde9c) [x32]

  pthread-based thread pool for C/C++ (shared object)

• dep: libre2-10 (>= 20160901) [x32]

  efficient, principled regular expression library

• dep: libstdc++6 (>= 14) [x32]

  GNU Standard C++ Library v3

• dep: libxnnpack0 (>= 0.0~git20221221.51a9875) [x32]

  High-efficiency floating-point neural network inference operators (libs)

• dep: python3 [all]

  interactive high-level object-oriented language (default python3 version)

• dep: python3-numpy [all]

  Python library for numerical computations (Python 3)

Изтегляне на onnxruntime-tools

Изтегляне за всички налични архитектури

Архитектура	Версия	Големина на пакета	Големина след инсталиране	Файлове
all	1.19.2+dfsg-9	7,2 кБ	26,0 кБ	[списък на файловете]
x32 (неофициална архитектура)	1.16.3+dfsg-7	3 565,7 кБ	13 169,0 кБ	[списък на файловете]