MCPcopy Create free account

hub / github.com/microsoft/TRELLIS / functions

Functions660 in github.com/microsoft/TRELLIS

⨍ Functions 660◇ Types & classes 116
↓ 101 callersMethodcuda
(self)
trellis/pipelines/base.py:64
↓ 71 callersMethodfloat
(self)
trellis/modules/sparse/basic.py:221
↓ 70 callersMethodreshape
(self, *shape)
trellis/modules/sparse/basic.py:236
↓ 57 callersMethodcpu
(self)
trellis/pipelines/base.py:67
↓ 52 callersMethodreplace
(self, feats: torch.Tensor, coords: Optional[torch.Tensor] = None)
trellis/modules/sparse/basic.py:243
↓ 30 callersMethoddetach
(self)
trellis/modules/sparse/basic.py:225
↓ 30 callersMethodload
Load a checkpoint. Should be called by all processes.
trellis/trainers/base.py:151
↓ 27 callersMethodto
(self, device: torch.device)
trellis/pipelines/base.py:60
↓ 26 callersMethodwrite
(self, x)
trellis/representations/gaussian/general_utils.py:118
↓ 23 callersMethodtype
(self, dtype)
trellis/modules/sparse/basic.py:203
↓ 20 callersMethodunbind
(self, dim: int)
trellis/modules/sparse/basic.py:240
↓ 14 callersMethodload_state_dict
(self, state_dict)
trellis/utils/data_utils.py:151
↓ 13 callersMethodfrom_pretrained
Load a pretrained model.
trellis/pipelines/base.py:22
↓ 13 callersMethodto
(self, dtype: torch.dtype)
trellis/modules/sparse/basic.py:177
↓ 9 callersMethodfull
(aabb, dim, value, dtype=torch.float32, device=None)
trellis/modules/sparse/basic.py:277
↓ 9 callersMethodlog
(self)
trellis/utils/elastic_utils.py:37
↓ 8 callersMethod__elemwise__
(self, other: Union[torch.Tensor, 'SparseTensor'], op: callable)
trellis/modules/sparse/basic.py:305
↓ 8 callersMethodregister_spatial_cache
Register a spatial cache. The spatial cache can be any thing you want to cache. The registery and retrieval of the cache is b
trellis/modules/sparse/basic.py:370
↓ 8 callersMethodstate_dict
(self)
trellis/utils/data_utils.py:145
↓ 7 callersMethodget_spatial_cache
Get a spatial cache.
trellis/modules/sparse/basic.py:381
↓ 7 callersMethodrender
Render the mesh. Args: mesh : meshmodel extrinsics (torch.Tensor): (4, 4) camera extrinsics intr
trellis/renderers/mesh_renderer.py:55
↓ 6 callersMethod_render_batch
Render a batch of representations. Args: reps: The dictionary of lists of representations. extrinsics: The [
trellis/trainers/vae/structured_latent_vae_mesh_dec.py:81
↓ 6 callersFunctiondict_reduce
Reduce a list of dictionaries. Leaf values must be scalars.
trellis/utils/general_utils.py:53
↓ 6 callersFunctionneed_process
(key)
dataset_toolkits/build_metadata.py:21
↓ 6 callersMethodsample
Sample from a model.
trellis/pipelines/samplers/base.py:11
↓ 5 callersFunctionl1_loss
(network_output, gt)
trellis/utils/loss_utils.py:14
↓ 5 callersFunctionrecursive_to_device
Recursively move all tensors in a data structure to a device.
trellis/utils/data_utils.py:9
↓ 5 callersMethodrun
Run training.
trellis/trainers/base.py:347
↓ 4 callersMethod__init__
( self, channels: int, out_channels: Optional[int] = None, norm_type: Literal[
trellis/models/sparse_structure_vae.py:23
↓ 4 callersMethod_inference_model
(self, model, x_t, t, cond=None, **kwargs)
trellis/pipelines/samplers/flow_euler.py:38
↓ 4 callersMethod_linear
(module: nn.Linear, x: Union[SparseTensor, torch.Tensor])
trellis/modules/sparse/attention/modules.py:78
↓ 4 callersFunctionget_file_hash
(file: str)
dataset_toolkits/utils.py:6
↓ 4 callersFunctionnorm_layer
Return a normalization layer.
trellis/models/sparse_structure_vae.py:10
↓ 4 callersMethodpreprocess_image
Preprocess the input image.
trellis/pipelines/trellis_image_to_3d.py:82
↓ 4 callersMethodsave_ply
(self, path, transform=[[1, 0, 0], [0, 0, -1], [0, 1, 0]])
trellis/representations/gaussian/gaussian_model.py:125
↓ 4 callersFunctionscaled_dot_product_attention
Apply scaled dot product attention. Args: qkv (torch.Tensor): A [N, L, 3, H, C] tensor containing Qs, Ks, and Vs.
trellis/modules/attention/full_attn.py:39
↓ 4 callersMethodsnapshot
Sample images from the model. NOTE: This function should be called by all processes.
trellis/trainers/base.py:220
↓ 3 callersMethod__cal_layout
(self, coords, batch_size)
trellis/modules/sparse/basic.py:123
↓ 3 callersMethod__cal_shape
(self, feats, coords)
trellis/modules/sparse/basic.py:117
↓ 3 callersMethod__init__
(self, channels: int, mlp_ratio: float = 4.0)
trellis/modules/transformer/blocks.py:50
↓ 3 callersMethod_perceptual_loss
Combination of L1, SSIM, and LPIPS loss.
trellis/trainers/vae/structured_latent_vae_mesh_dec.py:153
↓ 3 callersMethod_render_batch
Render a batch of representations. Args: reps: The dictionary of lists of representations. extrinsics: The [
trellis/trainers/vae/structured_latent_vae_gaussian.py:81
↓ 3 callersMethod_render_batch
Render a batch of representations. Args: reps: The dictionary of lists of representations. extrinsics: The [
trellis/trainers/vae/structured_latent_vae_rf_dec.py:75
↓ 3 callersMethod_state_dicts_to_master_params
Convert a state_dict to master params.
trellis/trainers/basic.py:160
↓ 3 callersMethodconvert_to_fp16
Convert the torso of the model to float16.
trellis/models/structured_latent_flow.py:198
↓ 3 callersMethodconvert_to_fp16
Convert the torso of the model to float16.
trellis/models/structured_latent_vae/base.py:89
↓ 3 callersFunctiondict_foreach
Recursively apply a function to all non-dictionary leaf values in a dictionary.
trellis/utils/general_utils.py:37
↓ 3 callersMethoddim
(self)
trellis/modules/sparse/basic.py:133
↓ 3 callersMethodencode_text
Encode the text.
trellis/trainers/flow_matching/mixins/text_conditioned.py:39
↓ 3 callersMethodfilter_metadata
(self, metadata: pd.DataFrame)
trellis/datasets/components.py:41
↓ 3 callersMethodforward
(self, input: SparseTensor)
trellis/modules/sparse/norm.py:18
↓ 3 callersMethodget_instance
(self, root: str, instance: str)
trellis/datasets/components.py:45
↓ 3 callersFunctionindent
Indent a string.
trellis/utils/general_utils.py:194
↓ 3 callersFunctionlpips
(img1, img2, value_range=(0, 1))
trellis/utils/loss_utils.py:73
↓ 3 callersFunctionread_file_dist
Read the binary file distributedly. File is only read once by the rank 0 process and broadcasted to other processes. Returns: da
trellis/utils/dist_utils.py:19
↓ 3 callersFunctionrender_frames
(sample, extrinsics, intrinsics, options={}, colors_overwrite=None, verbose=True, **kwargs)
trellis/utils/render_utils.py:72
↓ 3 callersFunctionssim
(img1, img2, window_size=11, size_average=True)
trellis/utils/loss_utils.py:39
↓ 3 callersFunctionyaw_pitch_r_fov_to_extrinsics_intrinsics
(yaws, pitchs, rs, fovs)
trellis/utils/render_utils.py:13
↓ 3 callersFunctionzero_module
Zero out the parameters of a module and return it.
trellis/modules/utils.py:35
↓ 2 callersMethod__init__
(self, dim: int, heads: int)
trellis/modules/attention/modules.py:9
↓ 2 callersMethod__init__
(self, factor: Union[int, Tuple[int, int, int], List[int]])
trellis/modules/sparse/spatial.py:64
↓ 2 callersMethod__init__
(self, channels: int, mlp_ratio: float = 4.0)
trellis/modules/sparse/transformer/blocks.py:12
↓ 2 callersMethod__init__
(self, roots: str, )
trellis/datasets/components.py:20
↓ 2 callersMethod_flip_normal
Flip normal to align with camera.
trellis/trainers/vae/structured_latent_vae_mesh_dec.py:136
↓ 2 callersMethod_forward_with_mem_ratio
Forward with a given memory ratio.
trellis/utils/elastic_utils.py:167
↓ 2 callersMethod_fused_pre
(self, x: Union[SparseTensor, torch.Tensor], num_fused: int)
trellis/modules/sparse/attention/modules.py:91
↓ 2 callersMethod_get_image
(self, root, instance)
trellis/datasets/structured_latent2render.py:48
↓ 2 callersMethod_get_latent
(self, root, instance)
trellis/datasets/structured_latent2render.py:76
↓ 2 callersMethod_init_image_cond_model
Initialize the image conditioning model.
trellis/pipelines/trellis_image_to_3d.py:70
↓ 2 callersMethod_init_text_cond_model
Initialize the text conditioning model.
trellis/pipelines/trellis_text_to_3d.py:66
↓ 2 callersMethod_master_params_to_state_dicts
Convert master params to dict of state_dicts.
trellis/trainers/basic.py:146
↓ 2 callersMethod_reshape_chs
(x: Union[SparseTensor, torch.Tensor], shape: Tuple[int, ...])
trellis/modules/sparse/attention/modules.py:85
↓ 2 callersMethod_rotary_embedding
(self, x: torch.Tensor, phases: torch.Tensor)
trellis/modules/attention/modules.py:34
↓ 2 callersMethodcheck_ddp
Check if DDP is working properly. Should be called by all process.
trellis/trainers/base.py:297
↓ 2 callersMethodcheck_ddp
Check if DDP is working properly. Should be called by all process.
trellis/trainers/basic.py:309
↓ 2 callersFunctioncosine_anealing
(optimizer, step, total_steps, start_lr, end_lr)
trellis/utils/postprocessing_utils.py:365
↓ 2 callersFunctioncycle
(data_loader: DataLoader)
trellis/utils/data_utils.py:50
↓ 2 callersMethoddecode_slat
Decode the structured latent. Args: slat (sp.SparseTensor): The structured latent. formats (List[str]): The
trellis/pipelines/trellis_text_to_3d.py:143
↓ 2 callersMethoddecode_slat
Decode the structured latent. Args: slat (sp.SparseTensor): The structured latent. formats (List[str]): The
trellis/pipelines/trellis_image_to_3d.py:195
↓ 2 callersMethoddevice
(self)
trellis/pipelines/base.py:51
↓ 2 callersMethoddevice
(self)
trellis/trainers/base.py:117
↓ 2 callersMethoddiffuse
Diffuse the data for a given number of diffusion steps. In other words, sample from q(x_t | x_0). Args: x_0: The
trellis/trainers/flow_matching/flow_matching.py:69
↓ 2 callersMethodencode_image
Encode the image. Args: image (Union[torch.Tensor, list[Image.Image]]): The image to encode Returns:
trellis/pipelines/trellis_image_to_3d.py:119
↓ 2 callersMethodencode_image
Encode the image.
trellis/trainers/flow_matching/mixins/image_conditioned.py:49
↓ 2 callersMethodencode_text
Encode the text.
trellis/pipelines/trellis_text_to_3d.py:82
↓ 2 callersFunctionfind_ckpt
(cfg)
train.py:17
↓ 2 callersMethodforward
(self, x: torch.Tensor)
trellis/modules/norm.py:6
↓ 2 callersMethodforward
(self, input: SparseTensor)
trellis/modules/sparse/nonlinearity.py:14
↓ 2 callersMethodforward
(self, *args, **kwargs)
trellis/utils/elastic_utils.py:176
↓ 2 callersMethodfrom_pretrained
Load a pretrained model. Args: path (str): The path to the model. Can be either local path or a Hugging Face repository.
trellis/pipelines/trellis_text_to_3d.py:42
↓ 2 callersMethodget_cond
Get the conditioning information for the model. Args: prompt (List[str]): The text prompt. Returns:
trellis/pipelines/trellis_text_to_3d.py:93
↓ 2 callersMethodget_cond
Get the conditioning information for the model. Args: image (Union[torch.Tensor, list[Image.Image]]): The image prompts.
trellis/pipelines/trellis_image_to_3d.py:145
↓ 2 callersMethodget_cond
Get the conditioning data.
trellis/trainers/flow_matching/flow_matching.py:106
↓ 2 callersFunctionget_defomed_verts
(v_pos : torch.Tensor, deform : torch.Tensor, res)
trellis/representations/mesh/utils_cube.py:59
↓ 2 callersFunctionget_dense_attrs
(coords : torch.Tensor, feats : torch.Tensor, res : int, sdf_init=True)
trellis/representations/mesh/utils_cube.py:50
↓ 2 callersMethodget_inference_cond
Get the conditioning data for inference.
trellis/trainers/flow_matching/flow_matching.py:112
↓ 2 callersMethodget_mem_ratio
(self, input_size)
trellis/utils/elastic_utils.py:29
↓ 2 callersFunctionget_renderer
(sample, **kwargs)
trellis/utils/render_utils.py:43
↓ 2 callersMethodget_sampler
Get the sampler for the diffusion process.
trellis/trainers/flow_matching/flow_matching.py:118
↓ 2 callersMethodget_v
Compute the velocity of the diffusion process at time t.
trellis/trainers/flow_matching/flow_matching.py:100
next →1–100 of 660, ranked by callers