Installing vai_q_tensorflow - 3.5 English

Vitis AI User Guide (UG1414)

Document ID
Release Date
3.5 English

There are two ways to install the vai_q_tensorflow:

Install Using Docker Containers

Vitis AI provides a Docker container for quantization tools, including vai_q_tensorflow. After running a container, activate the conda environment Vitis AI-tensorflow:

[docker] $ conda activate vitis-ai-tensorflow
Install the ​Vitis AI​​-tensorflow patch package inside the Docker container if there is a package-tensorflow patch package inside the Docker container:
[docker] $ sudo env CONDA_PREFIX=/opt/vitis_ai/conda/envs/vitis-ai-tensorflow/ PATH=/opt/vitis_ai/conda/bin:$PATH conda install patch_package.tar.bz2

Install Using Source Code

vai_q_tensorflow is an AMD-maintained plug-in tool for TensorFlow 1.15. It is open source in Vitis_AI_Quantizer. To build vai_q_tensorflow, run the following command:
[host] $ sh