---
language:
- zh
tags:
- hisilicon
- hispark
- npu
- openharmony
- modelzoo
- pytorch
---

# GraspNet

GraspNet是一种基于点云输入的多阶段抓取姿态预测模型，由抓取视角估计和抓取姿态生成两个阶段组成，通过特征提取、视角估计、局部特征提取、抓取参数估计和预测解码一系列处理，最终生成包含抓取评分、抓取宽度、抓取高度、抓取深度、旋转矩阵、抓取中心点和物体ID的预测结果，旨在解决机器人抓取任务中的6D抓取姿态估计问题。

## Mirror Metadata

- Hugging Face repo: shadow-cann/hispark-modelzoo-graspnet
- Portal model id: iodtp8ht0400
- Created at: 2026-02-09 19:42:15
- Updated at: 2026-02-12 11:24:22
- Category: 计算机视觉

## Framework

- PyTorch

## Supported OS

- OpenEuler

## Computing Power

- Hi3591PV100

## Tags

- 具身智能

## Detail Parameters

- 计算量: 71.121GFLOPs
- 输入: 720x1280
- 参数量: 2.397M

## Files In This Repo

- graspnet[该模型文件仅用于非商用].onnx (源模型 / 源模型下载; 源模型 / 源模型元数据)

## Upstream Links

- Portal card: https://gitbubble.github.io/hisilicon-developer-portal-mirror/model-detail.html?id=iodtp8ht0400
- Upstream repository: https://gitee.com/HiSpark/modelzoo/blob/master/samples/built-in/embodied_intelligence/GraspNet/README.md
- License reference: https://github.com/graspnet/graspnet-baseline/blob/main/LICENSE

## Notes

- This repository was mirrored from the HiSilicon Developer Portal model card and local downloads captured on 2026-03-27.
- File ownership follows the portal card mapping, not just filename similarity.
- Cover image: 1726646426140674_graspnet_16_9.jpg