HELP! Receiving error: nodes must be less than 1024

[复制链接] · 发表于 2019-7-4 15:19:27

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

只看该作者 · 发表于 2019-7-23 10:03:13

I have reported this issue, please wait for response

只看该作者 · 发表于 2019-8-13 15:21:51

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

只看该作者 · 发表于 2019-9-2 10:39:11

jefferyzhang 发表于 2019-7-23 10:03
I have reported this issue, please wait for response

any feedback??

只看该作者 · 发表于 2019-9-2 15:06:30

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?

只看该作者 · 发表于 2019-9-3 11:15:00

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.

HELP! Receiving error: nodes must be less than 1024

本帖子中包含更多资源