tutorial for pose estimation with TFlite that can run in raspberry pi

Question

Hi, 
 
 I need your help I am totally a newbie, I am struggling to run my pose estimation in raspberry pi 4 mode B (bullseye 11) 
 
 what I can encounter is I cant install tensorflow==2.4.1 abd opencv_python==4.6.0.66 , I was able to install tensorflow 2.4 but I encountered an error h5py lib is not found 
 
 error: /home/pi/tf_flow/env/lib/python3.7/site-packages/h5py/__init__.py:40: UserWarning: h5py is running against HDF5 1.10.6 when it was built against 1.10.4, this may cause problems '{0}.{1}.{2}'.format(*version.hdf5_built_version_tuple) 
 
 do you have simple tutorial for implementing pose estimation with TFlite in raspberry pi? thank you.

cstanton · Accepted Answer

denmark said: /home/pi/tf_flow/env/lib/python3.7/site-packages/h5py/__init__.py:40: UserWarning: h5py is running against HDF5 1.10.6 when it was built against 1.10.4, this may cause problems 
 This is simply complaining that the version of HDF5 that you have installed is more recent than the version expected by the script you're using to install. 
 You could try installing a specific version of HDF5 . pip install HDF5==1.10.4 
 Then try again.