Calculate Euclid distance between each two points. src^T * dst = xn * xm + yn * ym + zn * zm； sum(src^2, dim=-1) = xn*xn + yn*yn + zn*zn

Snowflake Point Deconvolution

Args: npoint: int, number of points to sample nsample: int, number of points in each local region radius:

Args: in_channel: int, input channel of points2 mlp: list of int use_points1: boolean, if use points

Args: npoint: int, number of points to sample nsample: int, number of points in each local region radius:

Snowflake Point Deconvolution

Snowflake Point Deconvolution

Initialize the weights

Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base class PreTrainedModel

Applies spectral norm to all modules within the scope of a CNF.

r""" Parameters ---------- grad_out : torch.Tensor (B, c, n) tensor with gradients of ouputs Returns

r""" Parameters ---------- grad_out : torch.Tensor (B, C, npoint, nsample) tensor of the gradients of the output

r""" Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).