MCPcopy Create free account

hub / github.com/microsoft/TRELLIS / functions

Functions660 in github.com/microsoft/TRELLIS

⨍ Functions 660◇ Types & classes 116
↓ 2 callersFunctionhammersley_sequence
(dim, n, num_samples)
trellis/utils/random_utils.py:19
↓ 2 callersMethodinject_sampler_multi_image
Inject a sampler with multiple images as condition. Args: sampler_name (str): The name of the sampler to inject.
trellis/pipelines/trellis_image_to_3d.py:286
↓ 2 callersFunctionl2_loss
(network_output, gt)
trellis/utils/loss_utils.py:18
↓ 2 callersFunctionload_balanced_group_indices
Split indices into groups with balanced load.
trellis/utils/data_utils.py:27
↓ 2 callersFunctionmain
(local_rank, cfg)
train.py:59
↓ 2 callersFunctionmodel_grads_to_master_grads
Copy the gradients from the model parameters into the master parameters from make_master_params().
trellis/trainers/utils.py:45
↓ 2 callersMethodrender
Render the octree. Args: octree (Octree): octree extrinsics (torch.Tensor): (4, 4) camera extrinsics
trellis/renderers/octree_renderer.py:201
↓ 2 callersFunctionrender_multiview
(sample, resolution=512, nviews=30)
trellis/utils/render_utils.py:103
↓ 2 callersMethodrun_multi_image
Run the pipeline with multiple images as condition Args: images (List[Image.Image]): The multi-view images of the assets
trellis/pipelines/trellis_image_to_3d.py:343
↓ 2 callersMethodrun_step
Run a training step.
trellis/trainers/base.py:341
↓ 2 callersMethodsample
Generate samples from the model using Euler method. Args: model: The model to sample from. noise: Th
trellis/pipelines/samplers/flow_euler.py:80
↓ 2 callersMethodsample_slat
Sample structured latent with the given conditioning. Args: cond (dict): The conditioning information.
trellis/pipelines/trellis_text_to_3d.py:167
↓ 2 callersMethodsample_slat
Sample structured latent with the given conditioning. Args: cond (dict): The conditioning information.
trellis/pipelines/trellis_image_to_3d.py:219
↓ 2 callersMethodsample_sparse_structure
Sample sparse structures with the given conditioning. Args: cond (dict): The conditioning information.
trellis/pipelines/trellis_image_to_3d.py:162
↓ 2 callersMethodsample_t
Sample timesteps.
trellis/trainers/flow_matching/flow_matching.py:130
↓ 2 callersFunctionscene_bbox
Returns the bounding box of the scene. Taken from Shap-E rendering script (https://github.com/openai/shap-e/blob/main/shap_e/rendering/blende
dataset_toolkits/blender_script/render.py:342
↓ 2 callersMethodselect
(cond, neg_cond, mask)
trellis/trainers/flow_matching/mixins/classifier_free_guidance.py:31
↓ 2 callersFunctionsparse_batch_broadcast
Broadcast a 1D tensor to a sparse tensor along the batch dimension then perform an operation. Args: input (torch.Tensor): 1D ten
trellis/modules/sparse/basic.py:392
↓ 2 callersFunctionsparse_scaled_dot_product_attention
Apply scaled dot product attention to a sparse tensor. Args: qkv (SparseTensor): A [N, *, 3, H, C] sparse tensor containing Qs, Ks,
trellis/modules/sparse/attention/full_attn.py:20
↓ 2 callersFunctionsphere_hammersley_sequence
(n, num_samples, offset=(0, 0), remap=False)
trellis/utils/random_utils.py:22
↓ 2 callersFunctionsphere_hammersley_sequence
(n, num_samples, offset=(0, 0))
dataset_toolkits/utils.py:36
↓ 2 callersFunctionunpack_state
(state: dict)
app_text.py:48
↓ 2 callersFunctionunpack_state
(state: dict)
app.py:78
↓ 2 callersMethodupdate_run_states
(self, input_size=None, mem_ratio=None)
trellis/utils/elastic_utils.py:21
↓ 2 callersMethodvis_cond
Visualize the conditioning data.
trellis/trainers/flow_matching/flow_matching.py:124
↓ 2 callersMethodvisualize_sample
Convert a sample to an image.
trellis/trainers/base.py:182
↓ 1 callersFunction__from_env
()
trellis/modules/attention/__init__.py:6
↓ 1 callersFunction__from_env
()
trellis/modules/sparse/__init__.py:7
↓ 1 callersFunction__from_env
()
trellis/modules/sparse/conv/__init__.py:6
↓ 1 callersFunction__getattr__
(name)
trellis/models/__init__.py:26
↓ 1 callersMethod__init__
(self, num_groups, num_channels, eps=1e-5, affine=True)
trellis/modules/sparse/norm.py:15
↓ 1 callersMethod__init__
(self, dim: int, heads: int)
trellis/modules/sparse/attention/modules.py:13
↓ 1 callersMethod__init__
(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, bias=True, indice_key=None)
trellis/modules/sparse/conv/conv_torchsparse.py:7
↓ 1 callersMethod__init__
(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, padding=None, bias=True, indice_key=None)
trellis/modules/sparse/conv/conv_spconv.py:8
↓ 1 callersMethod__init__
( self, channels: int, num_heads: int, mlp_ratio: float = 4.0, attn_mo
trellis/modules/sparse/transformer/modulated.py:14
↓ 1 callersMethod__init__
( self, channels: int, num_heads: int, mlp_ratio: float = 4.0, attn_mo
trellis/modules/transformer/modulated.py:13
↓ 1 callersMethod__init__
(self)
trellis/utils/elastic_utils.py:152
↓ 1 callersMethod__init__
( self, dataset: Dataset, shuffle: bool = True, seed: int = 0, drop_la
trellis/utils/data_utils.py:83
↓ 1 callersMethod__init__
(self, roots: str, *, latent_model: str, min_aesthetic_score: float = 5.0,
trellis/datasets/sparse_structure_latent.py:130
↓ 1 callersMethod__init__
(self, roots: str, *, latent_model: str, min_aesthetic_score: float = 5.0,
trellis/datasets/structured_latent.py:110
↓ 1 callersMethod__init__
( self, roots: str, image_size: int, latent_model: str, min_aesthetic_
trellis/datasets/structured_latent2render.py:22
↓ 1 callersMethod__init__
(self, hidden_size, frequency_embedding_size=256)
trellis/models/sparse_structure_flow.py:15
↓ 1 callersMethod__init__
( self, resolution: int, in_channels: int, model_channels: int, cond_c
trellis/models/structured_latent_flow.py:70
↓ 1 callersMethod__init__
( self, resolution: int, model_channels: int, latent_channels: int, nu
trellis/models/structured_latent_vae/decoder_mesh.py:73
↓ 1 callersMethod__init__
(self, vertices, faces, vertex_attrs=None, res=64 )
trellis/representations/mesh/cube2mesh.py:9
↓ 1 callersMethod__merge_sparse_cache
(self, other: 'SparseTensor')
trellis/modules/sparse/basic.py:290
↓ 1 callersMethod_add_sample
(self, memory, input_size, mem_ratio)
trellis/utils/elastic_utils.py:79
↓ 1 callersMethod_build_perturbation
(self)
trellis/models/structured_latent_vae/decoder_gs.py:60
↓ 1 callersMethod_calc_layout
(self)
trellis/models/structured_latent_vae/decoder_rf.py:59
↓ 1 callersMethod_calc_layout
(self)
trellis/models/structured_latent_vae/decoder_gs.py:67
↓ 1 callersMethod_calc_layout
(self)
trellis/representations/mesh/cube2mesh.py:74
↓ 1 callersMethod_calc_tsdf_loss
(self, reps : list[MeshExtractResult], depth_maps, extrinsics, intrinsics)
trellis/trainers/vae/structured_latent_vae_mesh_dec.py:129
↓ 1 callersMethod_delete_slat_dec
(self)
trellis/datasets/structured_latent.py:41
↓ 1 callersMethod_delete_ss_dec
(self)
trellis/datasets/sparse_structure_latent.py:40
↓ 1 callersFunction_dict_merge
Merge two dictionaries.
trellis/utils/general_utils.py:9
↓ 1 callersFunction_fill_holes
Rasterize a mesh from multiple views and remove invisible faces. Also includes postprocessing to: 1. Remove connected components that
trellis/utils/postprocessing_utils.py:22
↓ 1 callersMethod_fit_params
(self)
trellis/utils/elastic_utils.py:100
↓ 1 callersMethod_forward
(self, x: SparseTensor)
trellis/modules/sparse/transformer/blocks.py:65
↓ 1 callersMethod_forward
(self, x: SparseTensor, mod: torch.Tensor, context: torch.Tensor)
trellis/modules/sparse/transformer/blocks.py:135
↓ 1 callersMethod_forward
(self, x: SparseTensor, mod: torch.Tensor)
trellis/modules/sparse/transformer/modulated.py:57
↓ 1 callersMethod_forward
(self, x: SparseTensor, mod: torch.Tensor, context: torch.Tensor)
trellis/modules/sparse/transformer/modulated.py:142
↓ 1 callersMethod_forward
(self, x: torch.Tensor)
trellis/modules/transformer/blocks.py:99
↓ 1 callersMethod_forward
(self, x: torch.Tensor, context: torch.Tensor)
trellis/modules/transformer/blocks.py:165
↓ 1 callersMethod_forward
(self, x: torch.Tensor, mod: torch.Tensor)
trellis/modules/transformer/modulated.py:52
↓ 1 callersMethod_forward
(self, x: torch.Tensor, mod: torch.Tensor, context: torch.Tensor)
trellis/modules/transformer/modulated.py:132
↓ 1 callersMethod_get_feat
(self, root, instance)
trellis/datasets/sparse_feat2render.py:80
↓ 1 callersMethod_get_geo
(self, root, instance)
trellis/datasets/structured_latent2render.py:140
↓ 1 callersMethod_get_image
(self, root, instance)
trellis/datasets/sparse_feat2render.py:52
↓ 1 callersMethod_get_input_size
Get the size of the input data. Returns: int: The size of the input data.
trellis/utils/elastic_utils.py:157
↓ 1 callersMethod_get_input_size
Get the size of the input data. Returns: int: The size of the input data.
trellis/utils/elastic_utils.py:196
↓ 1 callersMethod_get_model_prediction
(self, model, x_t, t, cond=None, **kwargs)
trellis/pipelines/samplers/flow_euler.py:44
↓ 1 callersMethod_get_phases
(self, indices: torch.Tensor)
trellis/modules/attention/modules.py:28
↓ 1 callersMethod_get_regularization_loss
(self, reps: List[Gaussian])
trellis/trainers/vae/structured_latent_vae_gaussian.py:123
↓ 1 callersMethod_get_status
(self, z: SparseTensor, reps: List[Gaussian])
trellis/trainers/vae/structured_latent_vae_gaussian.py:103
↓ 1 callersMethod_init_image_cond_model
Initialize the image conditioning model.
trellis/trainers/flow_matching/mixins/image_conditioned.py:33
↓ 1 callersMethod_init_renderer
(self)
trellis/trainers/vae/structured_latent_vae_gaussian.py:74
↓ 1 callersMethod_init_renderer
(self)
trellis/trainers/vae/structured_latent_vae_mesh_dec.py:76
↓ 1 callersMethod_init_renderer
(self)
trellis/trainers/vae/structured_latent_vae_rf_dec.py:68
↓ 1 callersMethod_init_text_cond_model
Initialize the text conditioning model.
trellis/trainers/flow_matching/mixins/text_conditioned.py:22
↓ 1 callersFunction_install_blender
()
dataset_toolkits/render.py:19
↓ 1 callersFunction_install_blender
()
dataset_toolkits/render_cond.py:19
↓ 1 callersMethod_loading_slat_dec
(self)
trellis/datasets/structured_latent.py:29
↓ 1 callersMethod_loading_ss_dec
(self)
trellis/datasets/sparse_structure_latent.py:28
↓ 1 callersFunction_naive_sdpa
Naive implementation of scaled dot product attention.
trellis/modules/attention/full_attn.py:23
↓ 1 callersMethod_rope
(self, qkv: SparseTensor)
trellis/modules/sparse/attention/modules.py:99
↓ 1 callersMethod_sin_cos_embedding
Create sinusoidal position embeddings. Args: x: a 1-D Tensor of N indices Returns: an (N, D) Tensor
trellis/modules/transformer/blocks.py:20
↓ 1 callersFunction_ssim
(img1, img2, window, window_size, channel, size_average=True)
trellis/utils/loss_utils.py:49
↓ 1 callersMethod_tsdf_reg_loss
(rep: MeshExtractResult, depth_map: torch.Tensor, extrinsics: torch.Tensor, intrinsics: torch.Tensor)
trellis/trainers/vae/structured_latent_vae_mesh_dec.py:109
↓ 1 callersMethod_updown
(self, x: sp.SparseTensor)
trellis/models/structured_latent_flow.py:48
↓ 1 callersMethod_v_to_xstart_eps
(self, x_t, t, v)
trellis/pipelines/samplers/flow_euler.py:32
↓ 1 callersFunctionbake_texture
Bake texture to a mesh from multiple observations. Args: vertices (np.array): Vertices of the mesh. Shape (V, 3). faces (np.
trellis/utils/postprocessing_utils.py:276
↓ 1 callersFunctionblock_attn_config
Return the attention configuration of the model.
trellis/models/structured_latent_vae/base.py:10
↓ 1 callersFunctionbuild_rotation
(r)
trellis/representations/gaussian/general_utils.py:78
↓ 1 callersFunctionbuild_scaling_rotation
(s, r)
trellis/representations/gaussian/general_utils.py:101
↓ 1 callersFunctioncalc_serialization
Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz
trellis/modules/sparse/attention/serialized_attn.py:36
↓ 1 callersFunctioncalc_window_partition
Calculate serialization and partitioning for a set of coordinates. Args: tensor (SparseTensor): The input tensor. window_siz
trellis/modules/sparse/attention/windowed_attn.py:20
↓ 1 callersMethodcolor_losses
(self, reps, image, alpha, extrinsics, intrinsics)
trellis/trainers/vae/structured_latent_vae_mesh_dec.py:218
↓ 1 callersMethodcomput_face_normals
(self, verts, faces)
trellis/representations/mesh/cube2mesh.py:27
↓ 1 callersFunctionconstruct_dense_grid
construct a dense grid based on resolution
trellis/representations/mesh/utils_cube.py:8
↓ 1 callersMethodconstruct_list_of_attributes
(self)
trellis/representations/gaussian/gaussian_model.py:113
← previousnext →101–200 of 660, ranked by callers