About running demo

[Christopherlivy]

Hi.First thanks for sharing this!
I am new to the tensorflow and not familiar with CUDA, i use the MacBook Pro and I want to successfully run the demo first, I run the code and it says:
tensorflow.python.framework.errors_impl.NotFoundError: dlopen(./external/tf_nndistance_so.so, 6): image not found

I think its problem of CUDA implementations, is there a way not use the CUDA if I just want to use the pre-trained model to get a result first?

[Aquahugs]

Having same problem

[grEmsIsY]

@Christopherlivy Did you fixed yet?

[topinfrassi01]

If you only want to use the pre-trained model, you shouldn't need to load this library you might just modify the code to remove this dependency.

If you want to retrain and everything, I figured out that you don't really need the CUDA file to compute the loss as doing it directly with Tensorflow is almost as fast for meshes of ~6000 points (from what I tested). https://www.tensorflow.org/graphics/api_docs/python/tfg/nn/loss/chamfer_distance