DeepSDFStruct.deep_sdf.networks.resnet_positional_sdf_decoder

Classes

ResNetPositionalDeepSDFDecoder(latent_size, dims)

class DeepSDFStruct.deep_sdf.networks.resnet_positional_sdf_decoder.ResNetPositionalDeepSDFDecoder(latent_size, dims, dropout=None, dropout_prob=None, norm_layers=None, latent_in=None, xyz_in_all=False, latent_dropout=False, weight_norm=True, use_tanh=None, geom_dimension=3, activation_fun='tanh', positional_encoding=False, pe_levels=6, resnet=False, resnet_every=2)

Bases: torch.nn.modules.module.Module

forward(input)

input: [B, latent + xyz]

positional_encoding(xyz)

Applies sinusoidal positional encoding to each of the xyz dims. Output shape: [B, 3*(2*L+1)]