Yujin Chen

Hi, @mks0601. That is also my question! It seems that the _mano parameters_ here are hard to align with that in `manopth`. I think it might be that here the...

Hi. The same problem appears. Have you got the solution?

> Hi. The same problem appears. Have you got the solution? This can be solved by: `cd /home/machinelearning/.local/lib/python3.6/site-packages/tensorflow_core` `ln -s libtensorflow_framework.so.1 libtensorflow_framework.so`

> @TerenceCYJ > > Thank you. > > I've executed same commands, but problem is not solved. > Can you please once look into the same. Hi, @GopiRajuMatta. I just...

Hi, Gopi. I think you should check your pc_distance. After successful make, there should be a tf_nndistance_so.so In my setting, after make, `ls pc_distance` Get：`__init__.py __pycache__ tf_approxmatch.cu tf_approxmatch.py tf_nndistance.cpp tf_nndistance.cu.o...

Hi. In our experiments, we directly use MANO's pose parameters as Azimuth, Pitch, and Roll.

Please refer to `examples/losses.py#L143`, `examples/traineval_util.py#L378` and `examples/utils/freihandnet.py#L208`.

Please also refer to `examples/utils/hand_3d_model.py#L59`.

Hi. Sorry for the late reply. For 1, I don't think we need to reload/train the neural renderer. As far as my understanding, it is used to make photometric help...

Hi, maybe you can refer to #4