Toybrick

HELP! Receiving error: nodes must be less than 1024

lewis_brick

注册会员

积分
73
发表于 2019-7-4 15:19:27    查看: 8654|回复: 5 | [复制链接]    打印 | 显示全部楼层

I received the error message above when transferring caffemodel. anyone can give me a hint?

本帖子中包含更多资源

您需要 登录 才可以下载或查看,没有帐号?立即注册

x
回复

使用道具 举报

jefferyzhang

版主

积分
13210
发表于 2019-7-23 10:03:13 | 显示全部楼层
I have reported this issue, please wait for response
回复

使用道具 举报

lewis_brick

注册会员

积分
73
 楼主| 发表于 2019-8-13 15:21:51 | 显示全部楼层
jefferyzhang 发表于 2019-7-23 10:03
I have reported this issue, please wait for response

thanks for your notice! if node number is limited, quite lot of network won't be able to be deployed on rk3399 pro
looking forward to the response
回复

使用道具 举报

lewis_brick

注册会员

积分
73
 楼主| 发表于 2019-9-2 10:39:11 | 显示全部楼层
jefferyzhang 发表于 2019-7-23 10:03
I have reported this issue, please wait for response

any feedback??
回复

使用道具 举报

yhc

注册会员

积分
177
发表于 2019-9-2 15:06:30 | 显示全部楼层
Hi, NPU driver limits the number of nodes must be less than 1024

RKNN-Toolkit will do node merging when the model is converted. For example, conv+bn+scale will be merged into a conv, which will reduce the number of nodes.So, can you modify the model to match the merge rule?

Currently, none of the models we tested exceeded this limit. Can this model be provided for us to test?
回复

使用道具 举报

lewis_brick

注册会员

积分
73
 楼主| 发表于 2019-9-3 11:15:00 | 显示全部楼层
yhc 发表于 2019-9-2 15:06
Hi, NPU driver limits the number of nodes must be less than 1024

RKNN-Toolkit will do node merging  ...

The model I am using is hrnet for human keypoint detection. I transfer pytorch model to caffemodel, and then use rknn toolkit to obtain rknn model. during the rknn convertion, I encountered the error.
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

产品中心 购买渠道 开源社区 Wiki教程 资料下载 关于Toybrick


快速回复 返回顶部 返回列表