What do I see performance and numerical accuracy issues with quantized INT8 deep learning networks using GPU Coder in R2021a?

3 次查看（过去 30 天）
Bill Chou
Bill Chou 2021-3-24
回答： Bill Chou 2021-3-24
I’m generating code for a quantized deep learning network using GPU Coder but experiencing performance and numerical accuracy issues when using INT8 precision with cuDNN 8.
What versions of cuDNN are supported by GPU Coder in R2021a?

请先登录，再回答此问题。

采纳的回答

Bill Chou
Bill Chou 2021-3-24
In R2021a, GPU Coder supports cuDNN 8.1.0. For more information, see Installing Prerequisite Products (GPU Coder). It is recommended to use this version of cuDNN as other versions have significant performance and accuracy issues with INT8 workflows.
When using GPU Coder with cuDNN 8.0.x to generate CUDA code for a quantized deep learning network in INT8 precision, you may experience different issues depending on the version of cuDNN 8.0 used. The table below summarizes the issues you may experience.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Code Generation Fundamentals 的更多信息

标签

产品


版本

R2021a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by