Hristo Vassilev

@MMorafah I think you need to check what the tfpl.Convolution2DReparameterization layer passes to your custom prior function. Here's a source you can use (check the arguments for `make_normal_fn`): https://www.tensorflow.org/probability/api_docs/python/tfp/layers/default_mean_field_normal_fn @saurabhdeshpande93...

Not sure I can help you much as I have only done this with the tensorflow equivalent but the following code worked for me in a similar task: ``` import...

same or similar issue on Ubuntu 22.04 with no Chinese (or non-english) characters solution was to add '.' to the beginning of the path e.g. ``` class S3DIS: def __init__(self,...

> A simpler workaround that compiling pgeof: [rstudio/reticulate#1282 (comment)](https://github.com/rstudio/reticulate/issues/1282#issuecomment-1272473007) > > This is a bit hacky, but can be fixed by manually modifying where your `/home/somebody/miniconda3/envs/spt/bin/../lib/libstdc++*` symlinks point. > >...

> Hi, the results should have the same density as the original point cloud although we adopt two grid sizes. Pointcept will interpolate the downsampled point cloud to the original...