AMCT (TensorFlow)

OS and version

Ubuntu 20.04 (x86_64)

Download the required software release from the Ubuntu official website and install it. Run the following command to query the installation:

cat /etc/*release && uname -m

Quantization on the CPU or GPU is supported.

OS and version

Ubuntu 20.04 (AArch64)

Download the required software release from the Ubuntu official website and install it. Run the following command to query the installation:

cat /etc/*release && uname -m

Quantization on the CPU or GPU is supported.

CUDA Toolkit/CUDA Driver

12.6, 11.2, or 10.0

Obtain required packages for installation. For example, you can obtain the Toolkit package from the following URL, which contains the Driver package.

https://developer.nvidia.com/cuda-toolkit-archive

You need to install the CUDA software to perform quantization on the GPU.

• TensorFlow 2.19.0 works with CUDA 12.6.
• TensorFlow 2.6.5 works with CUDA 11.2.
• TensorFlow 1.15.0 works with CUDA 10.0.

Python

Python 3.11.x, Python 3.9.x, Python 3.8.x, Python 3.7.x

Python 3.9.2 is recommended.

For Ubuntu, Kylin V10 SP1, openEuler, and UOS, see Python 3.9.2 Installation on Ubuntu.

For EulerOS, see Python3.9.2 Installation on EulerOS.

• Ensure that the server has Internet access when installing dependencies.
• This document uses Python 3.9.2 as an example. The environment variables and installation commands are subject to the actual Python version.

TensorFlow

2.19.0, 2.6.5, or 1.15.0

For details, see Installing Dependencies.

Mapping between TensorFlow and Python versions:

• Version 2.19.0 works with Python3.11.x.
• Version 2.6.5 matches the following Python versions: Python 3.7.x (3.7.5–3.7.11), Python 3.8.x, and Python 3.9.x.
• Version 1.15.0 matches Python 3.7.x (3.7.5–3.7.11).

NumPy

2.0.0–2.1.3, 1.16.0–1.23.5, or 1.20.0–1.23.5

For details, see Installing Dependencies.

• If your TensorFlow version is 2.19.0, the NumPy version must be 2.0.0–2.1.3.
• If your TensorFlow version is 2.6.5, the NumPy version must be 1.20.0–1.23.5.
• If your TensorFlow version is 1.15.0, the NumPy version must be 1.16.0–1.23.5.

Protobuf

3.20.2+

For details, see Installing Dependencies.

• If your TensorFlow version is 2.19.0, the Protobuf version must be 3.20.3.
• If your TensorFlow version is 2.6.5 or 1.15.0, the Protobuf version must be 3.20.2 or later.