perceiver-pytorch icon indicating copy to clipboard operation
perceiver-pytorch copied to clipboard

How to use this model for point cloud?

Open sangyx opened this issue 3 years ago • 2 comments

Hi, I'm trying to use this model for point cloud task. However, the shape of my input data is (B, N, C), where B is the batch size, N is the number of points, C is the dim of feature. Which params I need to modify to apply this model to my task?

sangyx avatar Aug 30 '21 06:08 sangyx

You can try : model = Perceiver( input_channels = C, # number of channels for each token of the input input_axis = 1, etc)

It will suppose you have only one axis (here all of your points) and you have C channels like the dimension of the features.

Forbu avatar Sep 12 '21 21:09 Forbu

I think the point's location also needs to be converted to Fourier Features?

dnhkng avatar Oct 16 '21 08:10 dnhkng