Puts the model to the device. Args: device (device): pytorch device

move all tensor attributes to device. Args: device (torch.device): target device. Returns: Mesh: self.

load mesh from path. Args: path (str): path to mesh file, supports ply, obj, glb. clean (bool, optional): perform mes

write the mesh to a path. Args: path (str): path to write, supports ply, obj and glb.

iterator support

BufferGetAndValidate */

CIntToPy */

CIntToPy */

CIntToPy */

* Builds the index */

cat the img1 and img horizontally if horizon=True, else vertically. Resize img2 to fit the width of height of img1 using transforms.Resize()

This method has no effects in this class, but raises an exception if the expected size does not match */

Create a 1D, 2D, or 3D convolution module.

RaiseArgTupleInvalid */

Returns the dim'th component of the idx'th point in the class:

CIntToPy */

RaiseArgTupleInvalid */

BufferIndexError */

Returns occupancy probabilities for the sampled points. Args: p (tensor): points c (tensor): latent conditioned code

GetBuiltinName */

Get item.

:param img: torch tensor of shape [3,res,res] :param pixel_coords: [N,2] :param pixel_colors: [N,3] :param point_size: paint not only

Helper accessor to the dataset points:

set renderer

CIntToPy */

RaiseNeedMoreValuesToUnpack */

ExtTypeTest */

ExtTypeTest */

Write the sequence of args, with no separators, to the console and output files (if you've configured an output file).

Arguments: in_channels: int, number of channels in the input tensor. Default is 3 for RGB images. dep

MemviewSliceIsContig */

CIntFromPy */

BufferFallbackError */

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

GetBuiltinName */