You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Can someone please tell me how to install mmpose on a fresh Jetson Orin Nano?
The documentation didn’t specify the fact that pre-compiled mmcv are only for x86. So does it mean for Jetson, mmcv must be compiled from source?
As for compiling from source, I realise with 4GB RAM it’s very easy to run out of memory, so I have already got a 8GB swap setup.
And is it true that there’s no more mmcv-full from 2.x.x, only mmcv and mmcv-lite?
And I think if I use pip or mim to install to a Jetson, it will not find a .whl binary as no arm64 binaries are provided. So in that case, is pip / mim running the same process like ‘Compile mmcv from source’?
When compiling mmcv from source, do I only pass the argument ‘MMCV_WITH_OPS=1’ or are there more to make it CUDA enabled?
Does compiling mmpose depends on the version of mmcv?
Is there are more updated version of interoperability between
L4t / Python / PyTorch / CUDA against mmcv / mmdet / mmpose?
Does mmpose work with Jetpack 6 at all or do I have to downgrade to Jetpack 5?
Suggest a potential alternative/fix
No response
The text was updated successfully, but these errors were encountered:
📚 The doc issue
Can someone please tell me how to install mmpose on a fresh Jetson Orin Nano?
The documentation didn’t specify the fact that pre-compiled mmcv are only for x86. So does it mean for Jetson, mmcv must be compiled from source?
As for compiling from source, I realise with 4GB RAM it’s very easy to run out of memory, so I have already got a 8GB swap setup.
And is it true that there’s no more mmcv-full from 2.x.x, only mmcv and mmcv-lite?
And I think if I use pip or mim to install to a Jetson, it will not find a .whl binary as no arm64 binaries are provided. So in that case, is pip / mim running the same process like ‘Compile mmcv from source’?
When compiling mmcv from source, do I only pass the argument ‘MMCV_WITH_OPS=1’ or are there more to make it CUDA enabled?
Does compiling mmpose depends on the version of mmcv?
Is there are more updated version of interoperability between
L4t / Python / PyTorch / CUDA against mmcv / mmdet / mmpose?
Does mmpose work with Jetpack 6 at all or do I have to downgrade to Jetpack 5?
Suggest a potential alternative/fix
No response
The text was updated successfully, but these errors were encountered: