瑞萨电子 (Renesas Electronics Corporation)
搜索

DRP-AI Extension Pack (Pruning Tool)

成像

DRP-AI Extension Pack (Pruning Tool) Version 1.2.0

概览

DRP-AI for RZ/V2H and RZ/V2N supports a feature for efficiently calculating the pruned AI model. The DRP-AI Extension Pack provides a pruning function optimized for RZ/V2H and RZ/V2N. The DRP-AI optimized pruning function can be used in combination with this tool and PyTorch or TensorFlow training code.

What is pruning?

Nodes in a neural network are interconnected as shown in the figure. Methods of reducing the number of parameters by removing weights between nodes or removing nodes are referred to as “pruning”. A neural network to which pruning has not been applied is generally referred to as a dense neural network. And a neural network to which pruning has been applied is generally referred to as a sparse neural network. Applying pruning leads to a slight deterioration in the accuracy of the model but can reduce the power required by hardware and accelerate the inference process.

Dense neural network; after pruning: sparse neural network

How to embed the pruned model

The pruned model can be embedded using DRP-AI TVM. Refer to the DRP-AI TVM page on GitHub for details on TVM.
https://github.com/renesas-rz/rzv_drp-ai_tvm

Note: As shown in the figure, pruning is an optional function. (Dense model also can be embedded.)

DRP-AI Development Environment
  • Pruning functions optimized for RZ/V2H and RZ/V2N
  • Pruning ratio can be specified for balance between accuracy and power efficiency
  • Supports 2 pruning modes for improving accuracy (One Shot/Gradual)

DRP-AI Extension Pack Version 1.2.0 is available. (Jun. 2025)

  • Supported Ubuntu 22.04 and Python 3.10
  • Changed the supported TensorFlow version from 2.5.0 to 2.18.0
  • Supported PyTorch’s torch.nn.MultiheadAttention() layer for pruning Transformer structure.

下载

文档

设计和开发

支持

支持社区

支持社区

在线询问瑞萨电子工程社群的技术人员，快速获得技术支持。
获取支持
浏览常见问题解答

常见问题

浏览我们的知识库，了解常见问题的解答。
浏览常见问题解答
提交工单

提交工单

需要咨询技术性问题或提供非公开信息吗？
提交工单

视频和培训

This video provides an overview of DRP-AI TVM, focusing on the integration of AI into "Endpoint" devices for efficient real-time processing. Renesas' DRP-AI acts as a powerful accelerator, offering key features that enhance the performance and capabilities of endpoint AI applications.