Functions — github.com/DSL-Lab/StreamSplat

CodeHub MCPcopy Create free account

hub / github.com/DSL-Lab/StreamSplat / functions

Functions474 in github.com/DSL-Lab/StreamSplat

⨍ Functions 474◇ Types & classes 105

Methodattn_residual_func

(x: Tensor, attn_bias=None)

encoders/dinov2/layers/block.py:256

(ctx, grad_color, grad_radii, grad_depth, grad_alpha)

submodules/diff-gaussian-rasterization-orth/diff_gaussian_rasterization_kiui_orth/__init__.py:101

Functionbuild_model_from_cfg

(cfg, only_teacher=False)

encoders/dinov2/models/__init__.py:42

Functionbuild_scaling_rotation

utils/general_utils.py:102

FunctioncameraList_from_camInfos

(cam_infos, resolution_scale, args)

utils/camera_utils.py:71

Functioncamera_to_JSON

(id, camera : Camera)

utils/camera_utils.py:79

Functiondinov2_vitb14

DINOv2 ViT-B/14 model (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:81

Functiondinov2_vitb14_dd

(*, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:235

Functiondinov2_vitb14_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-B/14 backbone (optionally) pretrained on the LVD-142M dataset and trained on ImageNet-1k

encoders/dinov2/hub/classifiers.py:140

Functiondinov2_vitb14_ld

(*, layers: int = 4, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:149

Functiondinov2_vitb14_reg

DINOv2 ViT-B/14 model with registers (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:123

Functiondinov2_vitb14_reg_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-B/14 backbone with registers (optionally) pretrained on the LVD-142M dataset and trained

encoders/dinov2/hub/classifiers.py:216

Functiondinov2_vitg14

DINOv2 ViT-g/14 model (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:95

Functiondinov2_vitg14_dd

(*, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:243

Functiondinov2_vitg14_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-g/14 backbone (optionally) pretrained on the LVD-142M dataset and trained on ImageNet-1k

encoders/dinov2/hub/classifiers.py:178

Functiondinov2_vitg14_ld

(*, layers: int = 4, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:161

Functiondinov2_vitg14_reg

DINOv2 ViT-g/14 model with registers (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:153

Functiondinov2_vitg14_reg_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-g/14 backbone with registers (optionally) pretrained on the LVD-142M dataset and trained

encoders/dinov2/hub/classifiers.py:252

Functiondinov2_vitl14

DINOv2 ViT-L/14 model (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:88

Functiondinov2_vitl14_dd

(*, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:239

Functiondinov2_vitl14_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-L/14 backbone (optionally) pretrained on the LVD-142M dataset and trained on ImageNet-1k

encoders/dinov2/hub/classifiers.py:159

Functiondinov2_vitl14_ld

(*, layers: int = 4, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:155

Functiondinov2_vitl14_reg

DINOv2 ViT-L/14 model with registers (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:138

Functiondinov2_vitl14_reg_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-L/14 backbone with registers (optionally) pretrained on the LVD-142M dataset and trained

encoders/dinov2/hub/classifiers.py:234

Functiondinov2_vits14

DINOv2 ViT-S/14 model (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:74

Functiondinov2_vits14_dd

(*, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:231

Functiondinov2_vits14_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-S/14 backbone (optionally) pretrained on the LVD-142M dataset and trained on ImageNet-1k

encoders/dinov2/hub/classifiers.py:121

Functiondinov2_vits14_ld

(*, layers: int = 4, pretrained: bool = True, weights: Union[Weights, str] = Weights.NYU, **kwargs)

encoders/dinov2/hub/depthers.py:143

Functiondinov2_vits14_reg

DINOv2 ViT-S/14 model with registers (optionally) pretrained on the LVD-142M dataset.

encoders/dinov2/hub/backbones.py:108

Functiondinov2_vits14_reg_lc

Linear classifier (1 or 4 layers) on top of a DINOv2 ViT-S/14 backbone with registers (optionally) pretrained on the LVD-142M dataset and trained

encoders/dinov2/hub/classifiers.py:198

Functiondnormvdv

submodules/diff-gaussian-rasterization-orth/cuda_rasterizer/auxiliary.h:107

Functiondnormvdz

submodules/diff-gaussian-rasterization-orth/cuda_rasterizer/auxiliary.h:99

Functioneasy_cmap

(x: torch.Tensor)

utils/image_utils.py:21

Functioneval_sh

Evaluate spherical harmonics at unit directions using hardcoded SH polynomials. Works with torch/np/jnp. ... Can be 0 or more batch d

utils/sh_utils.py:58

Functioneval_shfs_4d

Evaluate spherical harmonics at unit directions using hardcoded SH polynomials. Works with torch/np/jnp. ... Can be 0 or more batch d

utils/sh_utils.py:115

Methodextract_timestamp

preprocess_depth_davis.py:71

Methodextract_timestamp

datasets/provider_vos.py:44

Methodextract_timestamp

datasets/provider_davis.py:44

(*args, **kwargs)

model/depth_anything/depth_anything_v2/dinov2.py:130

(*args, **kwargs)

encoders/dinov2/models/vision_transformer.py:152

Methodffn_residual_func

model/depth_anything/depth_anything_v2/dinov2_layers/block.py:86

Methodffn_residual_func

(x: Tensor, attn_bias=None)

model/depth_anything/depth_anything_v2/dinov2_layers/block.py:216

Methodffn_residual_func

encoders/dinov2/layers/block.py:99

Methodffn_residual_func

(x: Tensor, mod: Tensor)

encoders/dinov2/layers/block.py:133

Methodffn_residual_func

(x: Tensor, attn_bias=None)

encoders/dinov2/layers/block.py:259

model/depth_anything/depth_anything_v2/dinov2_layers/patch_embed.py:84

encoders/dinov2/layers/patch_embed.py:83

utils/general_utils.py:127

Functionfocal2fov

(focal, pixels)

utils/graphics_utils.py:123

(self, frames, depths, cond_times=None)

preprocess_depth_davis.py:135

(self, data, step_ratio=0.0)

model/encoder_model.py:68

(self, data, step_ratio=0.0)

model/splat_model_inference.py:37

(self, latent, condition=None)

model/model_utils.py:107

(self, feats, timestamp=None)

model/model_utils.py:277

Perform dynamic predictions.

model/model_utils.py:397

(self, frames, depths, cond_times=None)

model/model_utils.py:511

(self, frames, depths, cond_times=None)

model/model_utils.py:623

(self, data, step_ratio=0.0)

model/splat_model.py:169

model/depth_wrapper.py:36

model/transformer_utils.py:54

model/transformer_utils.py:62

model/transformer_utils.py:71

Args: query (torch.Tensor): query of shape (``N``, ``L_q``, ``E_qk``) key (torch.Tensor): key of shape (``N``, ``L_kv

model/transformer_utils.py:198

(self, x, index, condition=None)

model/transformer_utils.py:291

(self, x, index, condition)

model/transformer_utils.py:342

model/transformer_utils.py:372

(self, x, condition=None)

model/transformer_utils.py:396

(self, x, condition=None)

model/transformer_utils.py:415

(self, x, condition=None)

model/transformer_utils.py:431

(self, latent, condition)

model/transformer_utils.py:467

(self, latent, condition=None, reverse=False)

model/transformer_utils.py:503

model/transformer_utils.py:532

model/transformer_utils.py:571

model/depth_anything/depth_anything_v2/dpt.py:34

(self, out_features, patch_h, patch_w)

model/depth_anything/depth_anything_v2/dpt.py:117

model/depth_anything/depth_anything_v2/dinov2.py:38

(self, *args, is_training=False, **kwargs)

model/depth_anything/depth_anything_v2/dinov2.py:323

Forward pass. Args: x (tensor): input Returns: tensor: output

model/depth_anything/depth_anything_v2/util/blocks.py:57

Forward pass. Returns: tensor: output

model/depth_anything/depth_anything_v2/util/blocks.py:123

model/depth_anything/depth_anything_v2/dinov2_layers/drop_path.py:34

(self, x_or_x_list)

model/depth_anything/depth_anything_v2/dinov2_layers/block.py:245

(self, x: Tensor)

model/depth_anything/depth_anything_v2/dinov2_layers/layer_scale.py:27

(self, x: Tensor, attn_bias=None)

model/depth_anything/depth_anything_v2/dinov2_layers/attention.py:66

(self, x: Tensor)

model/depth_anything/depth_anything_v2/dinov2_layers/mlp.py:35

(self, x: Tensor)

model/depth_anything/depth_anything_v2/dinov2_layers/swiglu_ffn.py:29

(self, x: Tensor)

model/depth_anything/depth_anything_v2/dinov2_layers/patch_embed.py:69

(self, image: torch.Tensor, mod: torch.Tensor = None)

encoders/dinov2_wrapper.py:53

encoders/dinov2/hub/utils.py:36

encoders/dinov2/hub/classifiers.py:59

Forward function.

encoders/dinov2/hub/depth/decode_heads.py:292

(self, x, activate=True, norm=True)

encoders/dinov2/hub/depth/decode_heads.py:486

encoders/dinov2/hub/depth/decode_heads.py:507

encoders/dinov2/hub/depth/decode_heads.py:523

encoders/dinov2/hub/depth/decode_heads.py:577

encoders/dinov2/hub/depth/decode_heads.py:637

(self, *inputs)

encoders/dinov2/hub/depth/decode_heads.py:676

(self, inputs, img_metas)

encoders/dinov2/hub/depth/decode_heads.py:737

Calls either :func:`forward_train` or :func:`forward_test` depending on whether ``return_loss`` is ``True``. Note this setting will c

encoders/dinov2/hub/depth/encoder_decoder.py:249

encoders/dinov2/layers/drop_path.py:33

(self, x: Tensor, mod: Tensor)

encoders/dinov2/layers/block.py:129

← previous next →301–400 of 474, ranked by callers