MCPcopy Create free account

hub / github.com/facebookresearch/sam-3d-objects / functions

Functions784 in github.com/facebookresearch/sam-3d-objects

⨍ Functions 784◇ Types & classes 121
↓ 1 callersMethodto_representation
Convert a batch of network outputs to 3D representations. Args: x: The [N x * x C] sparse tensor output by the network.
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/decoder_rf.py:82
↓ 1 callersMethodto_representation
Convert a batch of network outputs to 3D representations. Args: x: The [N x * x C] sparse tensor output by the network.
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/decoder_gs.py:104
↓ 1 callersMethodto_representation
Convert a batch of network outputs to 3D representations. Args: x: The [N x * x C] sparse tensor output by the network.
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/decoder_mesh.py:167
↓ 1 callersFunctiontv_loss
(texture)
sam3d_objects/model/backbone/tdfy_dit/utils/postprocessing_utils.py:511
↓ 1 callersMethodunbind_qkv
(self, qkv)
sam3d_objects/model/backbone/tdfy_dit/modules/attention/modules.py:278
↓ 1 callersMethodunpack_tensors
(self, h_others, indicies_mapping)
sam3d_objects/model/backbone/tdfy_dit/modules/attention/modules.py:303
↓ 1 callersFunctionunpatchify
Unpatchify a tensor. Args: x (torch.Tensor): (N, C, *spatial) tensor patch_size (int): Patch size
sam3d_objects/model/backbone/tdfy_dit/modules/spatial.py:42
↓ 1 callersFunctionzero_prediction_decoder
()
sam3d_objects/pipeline/inference_utils.py:570
FunctionLearntPositionEmbedder
(model_channels, token_len)
sam3d_objects/model/backbone/tdfy_dit/models/mm_latent.py:84
FunctionPILtoTorch
(pil_image, resolution)
sam3d_objects/model/backbone/tdfy_dit/representations/gaussian/general_utils.py:24
FunctionRGB2SH
(rgb)
sam3d_objects/model/backbone/tdfy_dit/renderers/sh_utils.py:124
FunctionRandomPositionEmbedder
(model_channels, token_len)
sam3d_objects/model/backbone/tdfy_dit/models/mm_latent.py:75
FunctionSH2RGB
(sh)
sam3d_objects/model/backbone/tdfy_dit/renderers/sh_utils.py:128
FunctionShapePositionEmbedder
(model_channels, resolution, patch_size)
sam3d_objects/model/backbone/tdfy_dit/models/mm_latent.py:60
Method__add__
( self, other: Union[torch.Tensor, "SparseTensor", float] )
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:366
Method__call__
( self, image: Union[Image.Image, np.ndarray], mask: Optional[Union[None, Image.Image,
notebook/inference.py:101
Method__call__
Generates a mesh based on the specified sparse voxel structures. Args: cube_attrs [Nx21] : Sparse Tensor attrs about cube
sam3d_objects/model/backbone/tdfy_dit/representations/mesh/cube2mesh.py:101
Method__call__
(self, voxelgrid_vertices, scalar_field, cube_idx, resolution, qef_reg_scale=1e-3, weight_sca
sam3d_objects/model/backbone/tdfy_dit/representations/mesh/flexicubes/flexicubes.py:57
Method__call__
( self, image: torch.Tensor, mask: Optional[torch.Tensor] = None )
sam3d_objects/data/dataset/tdfy/img_and_mask_transforms.py:67
Method__call__
(self, image)
sam3d_objects/pipeline/depth_models/base.py:12
Method__call__
(self, image)
sam3d_objects/pipeline/depth_models/moge.py:5
Method__call__
(self, *args: Any, **kwargs: Any)
sam3d_objects/config/utils.py:104
Method__call__
(self, *args: Any, **kwargs: Any)
sam3d_objects/config/utils.py:134
Method__getitem__
(self, idx)
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:406
Method__init__
(self, config_file: str, compile: bool = False)
notebook/inference.py:85
Method__init__
(self, seed_or_generator: Optional[Union[int, torch.Generator]] = None)
sam3d_objects/model/backbone/generator/base.py:7
Method__init__
( self, backbone, # backbone should be a backbone/generator (e.g. DDPM/DDIM/FlowMatching)
sam3d_objects/model/backbone/generator/classifier_free_guidance.py:66
Method__init__
(self, *args, use_unconditional_from_flow_matching=False, **kwargs)
sam3d_objects/model/backbone/generator/classifier_free_guidance.py:226
Method__init__
(self, **kwargs)
sam3d_objects/model/backbone/generator/flow_matching/solver.py:56
Method__init__
( self, reverse_fn: Callable, sigma_min: float = 0.0, # 0. = rectifier flow i
sam3d_objects/model/backbone/generator/flow_matching/model.py:46
Method__init__
( self, no_shortcut=False, self_consistency_prob=0.25, shortcut_loss_weight=1.
sam3d_objects/model/backbone/generator/shortcut/model.py:21
Method__init__
(self, hidden_size: int, in_channels: int = 3)
sam3d_objects/model/backbone/tdfy_dit/modules/attention/modules.py:25
Method__init__
( self, channels: int, num_heads: int, ctx_channels: Optional[int] = None,
sam3d_objects/model/backbone/tdfy_dit/modules/attention/modules.py:88
Method__init__
( self, channels: int, num_heads: int, ctx_channels: Optional[int] = None,
sam3d_objects/model/backbone/tdfy_dit/modules/attention/modules.py:181
Method__init__
(self, in_features, out_features, bias=True)
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/linear.py:10
Method__init__
(self, factor: Union[int, Tuple[int, ...], List[int]])
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/spatial.py:16
Method__init__
(self)
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/spatial.py:105
Method__init__
(self, normalized_shape, eps=1e-5, elementwise_affine=True)
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/norm.py:35
Method__init__
( self, feats: torch.Tensor, coords: torch.Tensor, shape: Optional[torch.Size]
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:37
Method__init__
(self, activation: nn.Module)
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/nonlinearity.py:25
Method__init__
( self, channels: int, num_heads: int, ctx_channels: Optional[int] = None,
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/attention/modules.py:35
Method__init__
( self, in_channels, out_channels, kernel_size, stride=1, dila
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/conv/conv_spconv.py:93
Method__init__
( self, channels: int, num_heads: int, mlp_ratio: float = 4.0, attn_mo
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/transformer/blocks.py:30
Method__init__
( self, channels: int, ctx_channels: int, num_heads: int, mlp_ratio: f
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/transformer/blocks.py:92
Method__init__
( self, channels: int, ctx_channels: int, num_heads: int, mlp_ratio: f
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/transformer/modulated.py:95
Method__init__
(self, channels: int, in_channels: int = 3)
sam3d_objects/model/backbone/tdfy_dit/modules/transformer/blocks.py:14
Method__init__
( self, channels: int, num_heads: int, mlp_ratio: float = 4.0, attn_mo
sam3d_objects/model/backbone/tdfy_dit/modules/transformer/blocks.py:77
Method__init__
( self, channels: int, ctx_channels: int, num_heads: int, mlp_ratio: f
sam3d_objects/model/backbone/tdfy_dit/modules/transformer/blocks.py:133
Method__init__
( self, channels: int, ctx_channels: int, num_heads: int, mlp_ratio: f
sam3d_objects/model/backbone/tdfy_dit/modules/transformer/modulated.py:90
Method__init__
( self, channels: int, ctx_channels: int, num_heads: int, mlp_ratio: f
sam3d_objects/model/backbone/tdfy_dit/modules/transformer/modulated.py:179
Method__init__
(self, rendering_options={})
sam3d_objects/model/backbone/tdfy_dit/renderers/gaussian_render.py:222
Method__init__
(self, rendering_options={})
sam3d_objects/model/backbone/tdfy_dit/renderers/octree_renderer.py:193
Method__init__
( self, in_channels, model_channels: int, pos_embedder: Callable[[], torch.Tensor] )
sam3d_objects/model/backbone/tdfy_dit/models/mm_latent.py:13
Method__init__
( self, resolution: int, in_channels: int, model_channels: int, cond_c
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_flow.py:73
Method__init__
(self, *args, **kwargs)
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_flow.py:258
Method__init__
( self, latent_mapping: dict, latent_share_transformer: dict = {}, *args,
sam3d_objects/model/backbone/tdfy_dit/models/mot_sparse_structure_flow.py:174
Method__init__
( self, in_channels: int, out_channels: int, mode: Literal["conv", "avgpool"]
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_vae.py:62
Method__init__
( self, in_channels: int, out_channels: int, mode: Literal["conv", "nearest"]
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_vae.py:89
Method__init__
( self, in_channels: int, latent_channels: int, num_res_blocks: int, c
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_vae.py:130
Method__init__
( self, out_channels: int, latent_channels: int, num_res_blocks: int,
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_vae.py:240
Method__init__
(self, *args, **kwargs)
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_vae.py:347
Method__init__
(self, sample_posterior=True, return_raw=True, *args, **kwargs)
sam3d_objects/model/backbone/tdfy_dit/models/sparse_structure_vae.py:369
Method__init__
( self, channels: int, emb_channels: int, out_channels: Optional[int] = None,
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_flow.py:16
Method__init__
(self, *args, **kwargs)
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_flow.py:305
Method__init__
(self, hidden_size, frequency_embedding_size=256, freeze=False)
sam3d_objects/model/backbone/tdfy_dit/models/timestep_embedder.py:12
Method__init__
( self, resolution: int, model_channels: int, latent_channels: int, nu
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/decoder_rf.py:13
Method__init__
(self, *args, **kwargs)
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/decoder_gs.py:161
Method__init__
( self, in_channels: int, model_channels: int, num_blocks: int, num_he
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/base.py:42
Method__init__
( self, channels: int, resolution: int, out_channels: Optional[int] = None,
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/decoder_mesh.py:27
Method__init__
(self, *args, **kwargs)
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/decoder_mesh.py:193
Method__init__
(self, *args, **kwargs)
sam3d_objects/model/backbone/tdfy_dit/models/structured_latent_vae/encoder.py:82
Method__init__
a model to generate a mesh from sparse features structures using flexicube
sam3d_objects/model/backbone/tdfy_dit/representations/mesh/cube2mesh.py:55
Method__init__
(self, device="cuda")
sam3d_objects/model/backbone/tdfy_dit/representations/mesh/flexicubes/flexicubes.py:26
Method__init__
( self, aabb: list, sh_degree: int = 0, mininum_kernel_size: float = 0.0,
sam3d_objects/model/backbone/tdfy_dit/representations/gaussian/gaussian_model.py:9
Method__init__
(self, silent)
sam3d_objects/model/backbone/tdfy_dit/representations/gaussian/general_utils.py:127
Method__init__
( self, resolution: int, aabb: list, sh_degree: int = 0, rank: int = 8
sam3d_objects/model/backbone/tdfy_dit/representations/radiance_field/strivec.py:10
Method__init__
( self, depth, aabb=[0, 0, 0, 1, 1, 1], sh_degree=2, primitive="voxel"
sam3d_objects/model/backbone/tdfy_dit/representations/octree/octree_dfs.py:54
Method__init__
( self, input_size: int = 256, patch_size: int = 8, embed_dim: int = 768,
sam3d_objects/model/backbone/dit/embedder/pointmap.py:20
Method__init__
( self, embedder_list: List[Tuple[nn.Module, List[Tuple[str, Optional[str]]]]], use_po
sam3d_objects/model/backbone/dit/embedder/embedder_fuser.py:23
Method__init__
(self, remap_type: str = "exp")
sam3d_objects/model/backbone/dit/embedder/point_remapper.py:11
Method__init__
( self, backbone: Dino, )
sam3d_objects/model/backbone/dit/embedder/dino.py:133
Method__init__
Llama3 FeedForward layer https://github.com/meta-llama/llama3/blob/a0940f9cf7065d45bb6675660f80d305c041a754/llama/model.py#L193
sam3d_objects/model/layers/llama3/ff.py:8
Method__init__
( self, resize_and_make_square_kwargs: Optional[Dict] = None, object_crop_kwargs: Opti
sam3d_objects/data/dataset/tdfy/img_and_mask_transforms.py:53
Method__init__
(self, use_scene_scale: bool = True, quantile_drop_threshold: float = 0.1, clip_beyond
sam3d_objects/data/dataset/tdfy/img_and_mask_transforms.py:520
Method__init__
(self, clip_beyond_scale: Optional[float] = None, use_scene_scale: bool = True,
sam3d_objects/data/dataset/tdfy/img_and_mask_transforms.py:619
Method__init__
(self, clip_beyond_scale: Optional[float] = None, use_scene_scale: bool = True, log_di
sam3d_objects/data/dataset/tdfy/img_and_mask_transforms.py:678
Method__init__
(self, shift_log: torch.Tensor = 0.0, scale_log: torch.Tensor = 1.0)
sam3d_objects/data/dataset/tdfy/pose_target.py:776
Method__init__
( self, *args, depth_model, layout_post_optimization_method=layout_post_optimization, layout_post_opti
sam3d_objects/pipeline/inference_pipeline_pointmap.py:93
Method__init__
( self, ss_generator_config_path, ss_generator_ckpt_path, slat_generator_confi
sam3d_objects/pipeline/inference_pipeline.py:54
Method__init__
(self, model, device="cuda")
sam3d_objects/pipeline/depth_models/base.py:6
Method__init__
(self, path, /, *args, **kwargs)
sam3d_objects/config/utils.py:100
Method__init__
(self, config)
sam3d_objects/config/utils.py:129
Method__init__
(self, path, *args, **kwargs)
sam3d_objects/config/utils.py:140
Method__mul__
( self, other: Union[torch.Tensor, "SparseTensor", float] )
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:386
Method__neg__
(self)
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:346
Method__post_init__
(self)
sam3d_objects/data/dataset/tdfy/preprocessor.py:44
Method__post_init__
(self)
sam3d_objects/data/dataset/tdfy/pose_target.py:158
Method__radd__
( self, other: Union[torch.Tensor, "SparseTensor", float] )
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:371
Method__rmul__
( self, other: Union[torch.Tensor, "SparseTensor", float] )
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:391
Method__rsub__
( self, other: Union[torch.Tensor, "SparseTensor", float] )
sam3d_objects/model/backbone/tdfy_dit/modules/sparse/basic.py:381
← previousnext →401–500 of 784, ranked by callers