Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

为什么rknpu和rknpu2的output_attr.dim排序是相反的? #57

Open
SpiceGL opened this issue Nov 24, 2023 · 0 comments
Open

为什么rknpu和rknpu2的output_attr.dim排序是相反的? #57

SpiceGL opened this issue Nov 24, 2023 · 0 comments

Comments

@SpiceGL
Copy link

SpiceGL commented Nov 24, 2023

我在rv1126上使用的rknpu和rknn-toolkit版本为1.7.1,在rk3588上使用的rknpu2和rknn-toolkit2版本为1.4.0。
使用同一个模型(YOLOv7)进行测试,使用通用API进行推理。
在rv1126上,rknn_outputs_get获取到的输出outputs的buf数据的排列顺序确实是NCHW(1,3,400,7),但对应的output_attr.dims值按顺序是(7,400,3,1)。
而在rk3588上buf数据的顺序和output_attr.dims的顺序是一致的,都是(1,3,400,7)。
rv1126上这种有点反直觉的情况我有些不太理解。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant