xingyul/flownet3d

pre-trained model performance

ziruiw-dev opened this issue · 2 comments

ziruiw-dev commented

Hi xingyul,

Thanks for the code and the pre-trained model.
I run the evaluation.py over the pre-trained model you provided but I got performance output below:

eval mean loss: 0.404094
eval mean EPE 3D: 0.790930
eval mean ACC 3D: 0.000854
eval mean ACC 3D 2: 0.006859

maybe it's an untrained model? or did I do it in the wrong way?

Best,
Zirui

xEnVrE commented

Hi @Ryan-Zirui-Wang

I had similar issues as yours due to wrong sm architecture in the Makefile of custom tensorflow operators. As an example, consider the following

flownet3d/tf_ops/3d_interpolation/Makefile

Line 12 in 3a4b3b6

arch = sm_61

where sm_61 is used while my GPU required sm_60.

After rebuild of operators with the correct architecture I had the right results. Hope this helps.

ziruiw-dev commented

Hi @xEnVrE,

Many thanks for your help. Mine is sm_61 and I did try to re-compile operators but the problem remains... so it must be something wrong at my side if the pre-trained model works on your machine.

Best,
Zirui