Functions — github.com/cvlab-kaist/PF3plat

CodeHub MCPcopy Create free account

hub / github.com/cvlab-kaist/PF3plat / functions

Functions843 in github.com/cvlab-kaist/PF3plat

⨍ Functions 843◇ Types & classes 197↳ Endpoints 2

(self, x, emb, context=None)

src/model/encoder/costvolume/ldm_unet/unet.py:82

(self, x, y=None)

src/model/encoder/costvolume/ldm_unet/unet.py:115

src/model/encoder/costvolume/ldm_unet/unet.py:136

(self, x, y=None)

src/model/encoder/costvolume/ldm_unet/unet.py:171

Apply the block to a Tensor, conditioned on a timestep embedding. :param x: an [N x C x ...] Tensor of features. :param emb:

src/model/encoder/costvolume/ldm_unet/unet.py:276

src/model/encoder/costvolume/ldm_unet/unet.py:362

(self, x, y=None)

src/model/encoder/costvolume/ldm_unet/unet.py:441

Apply QKV attention. :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte

src/model/encoder/costvolume/ldm_unet/unet.py:538

Apply QKV attention. :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor afte

src/model/encoder/costvolume/ldm_unet/unet.py:582

Apply the model to an input batch. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a 1-D batch of timesteps.

src/model/encoder/costvolume/ldm_unet/unet.py:1098

(self, x, context=None)

src/model/encoder/costvolume/ldm_unet/unet.py:1237

src/model/encoder/costvolume/ldm_unet/attention.py:40

src/model/encoder/costvolume/ldm_unet/attention.py:61

src/model/encoder/costvolume/ldm_unet/attention.py:86

src/model/encoder/costvolume/ldm_unet/attention.py:124

(self, x, context=None, mask=None)

src/model/encoder/costvolume/ldm_unet/attention.py:168

(self, x, context=None)

src/model/encoder/costvolume/ldm_unet/attention.py:206

(self, x, context=None)

src/model/encoder/costvolume/ldm_unet/attention.py:250

(ctx, run_function, length, *args)

src/model/encoder/costvolume/ldm_unet/util.py:121

src/model/encoder/costvolume/ldm_unet/util.py:228

src/model/encoder/costvolume/ldm_unet/util.py:233

src/model/encoder/costvolume/ldm_unet/util.py:237

( self, extrinsics: Float[Tensor, "*#batch 4 4"], intrinsics: Float[Tensor, "*#batch 3

src/model/encoder/common/gaussian_adapter.py:48

(self, x, *args, **kwargs)

src/model/unidepth/encoder.py:12

src/model/unidepth/backbones/dinov2.py:107

(self, x, masks=None)

src/model/unidepth/backbones/dinov2.py:319

src/model/unidepth/backbones/convnext.py:134

src/model/unidepth/backbones/convnext.py:218

src/model/unidepth/backbones/convnext.py:299

(self, x, masks=None)

src/model/unidepth/backbones/convnext.py:469

src/model/unidepth/backbones/convnext2.py:129

src/model/unidepth/backbones/convnext2.py:150

src/model/unidepth/backbones/convnext2.py:179

src/model/unidepth/backbones/convnext2.py:265

src/model/unidepth/backbones/metadinov2/drop_path.py:36

(self, x_or_x_list)

src/model/unidepth/backbones/metadinov2/block.py:273

src/model/unidepth/backbones/metadinov2/dino_head.py:44

(self, x: Tensor)

src/model/unidepth/backbones/metadinov2/layer_scale.py:27

(self, x: Tensor, attn_bias=None)

src/model/unidepth/backbones/metadinov2/attention.py:69

(self, x: Tensor)

src/model/unidepth/backbones/metadinov2/mlp.py:35

(self, x: Tensor)

src/model/unidepth/backbones/metadinov2/swiglu_ffn.py:29

(self, x: Tensor)

src/model/unidepth/backbones/metadinov2/patch_embed.py:71

Computes the spherical harmonics.

src/model/unidepth/utils/sht.py:1439

( self, x: torch.Tensor, mask: Optional[torch.Tensor] = None )

src/model/unidepth/utils/positional_embedding.py:29

src/model/unidepth/utils/positional_embedding.py:80

(self, t, start_index=0)

src/model/unidepth/utils/positional_embedding.py:157

src/model/unidepth/utils/positional_embedding.py:212

src/model/unidepth/layers/drop_path.py:24

src/model/unidepth/layers/convnext.py:33

(self, x: torch.Tensor)

src/model/unidepth/layers/upsample.py:40

(self, x: torch.Tensor)

src/model/unidepth/layers/upsample.py:74

(self, x: torch.Tensor)

src/model/unidepth/layers/upsample.py:129

( self, x: torch.Tensor, mask: Optional[torch.Tensor] = None )

src/model/unidepth/layers/positional_encoding.py:30

src/model/unidepth/layers/positional_encoding.py:81

(self, t, start_index=0)

src/model/unidepth/layers/positional_encoding.py:173

src/model/unidepth/layers/positional_encoding.py:228

(self, x: torch.Tensor)

src/model/unidepth/layers/layer_scale.py:16

( self, x: torch.Tensor, attn_bias: torch.Tensor | None = None, context: torch

src/model/unidepth/layers/attention.py:39

( self, x: torch.Tensor, attn_bias: torch.Tensor | None = None, context: torch

src/model/unidepth/layers/attention.py:149

( self, x: torch.Tensor, attn_bias: torch.Tensor | None = None, context: torch

src/model/unidepth/layers/attention.py:278

src/model/unidepth/layers/mlp.py:20

(self, x: torch.Tensor)

src/model/unidepth/layers/mlp.py:48

(self, x: torch.Tensor)

src/model/unidepth/layers/activation.py:7

(self, x: torch.Tensor)

src/model/unidepth/layers/activation.py:13

(self, x: torch.Tensor, splits: torch.Tensor)

src/model/unidepth/unidepthv2/decoder.py:27

(self, features, cls_tokens, pos_embed)

src/model/unidepth/unidepthv2/decoder.py:67

(self, features, cls_tokens, rays)

src/model/unidepth/unidepthv2/decoder.py:136

( self, features: torch.Tensor, rays_hr: torch.Tensor, pos_embed, level_embed )

src/model/unidepth/unidepthv2/decoder.py:320

(self, inputs, image_metas)

src/model/unidepth/unidepthv2/decoder.py:431

(self, inputs, image_metas, num_views)

src/model/unidepth/unidepthv2/unidepthv2.py:138

( self, gaussians: Gaussians, extrinsics: Float[Tensor, "batch view 4 4"], int

src/model/decoder/decoder.py:38

( self, gaussians: Gaussians, extrinsics: Float[Tensor, "batch view 4 4"], int

src/model/decoder/decoder_splatting_cuda.py:35

(self, data: dict)

src/model/LightGlue/lightglue/sift.py:198

encode position vector

src/model/LightGlue/lightglue/lightglue.py:69

get confidence tokens

src/model/LightGlue/lightglue/lightglue.py:82

(self, q, k, v, mask: Optional[torch.Tensor] = None)

src/model/LightGlue/lightglue/lightglue.py:106

( self, x: torch.Tensor, encoding: torch.Tensor = None, mask: Optional[torch.T

src/model/LightGlue/lightglue/lightglue.py:152

( self, x0: torch.Tensor, x1: torch.Tensor, mask: Optional[torch.Tensor] = None )

src/model/LightGlue/lightglue/lightglue.py:195

( self, desc0, desc1, encoding0, encoding1, mask0: Optional[to

src/model/LightGlue/lightglue/lightglue.py:233

build assignment matrix from descriptors

src/model/LightGlue/lightglue/lightglue.py:281

Match keypoints and descriptors between two images Input (dict): image0: dict keypoints: [B x M x 2]

src/model/LightGlue/lightglue/lightglue.py:450

:param scores_map: Bx1xHxW :param descriptor_map: BxCxHxW :param sub_pixel: whether to use sub-pixel keypoint detection

src/model/LightGlue/lightglue/aliked.py:127

src/model/LightGlue/lightglue/aliked.py:328

src/model/LightGlue/lightglue/aliked.py:412

(self, x: torch.Tensor)

src/model/LightGlue/lightglue/aliked.py:460

(self, x, keypoints)

src/model/LightGlue/lightglue/aliked.py:534

(self, data: dict)

src/model/LightGlue/lightglue/aliked.py:740

(self, data: dict)

src/model/LightGlue/lightglue/dog_hardnet.py:15

Compute keypoints, scores, descriptors for image

src/model/LightGlue/lightglue/superpoint.py:150

( self, prediction: DecoderOutput, batch: BatchedExample, gaussians: Gaussians

src/loss/loss_mse.py:23

Compute the correspondence loss

src/loss/loss_pose.py:29

( self, prediction: DecoderOutput, # prediction2: DecoderOutput, # prediction3

src/loss/loss_lpips.py:36

( self, prediction: DecoderOutput, batch: BatchedExample, gaussians: Gaussians

src/loss/loss_multissim.py:25

src/model/unidepth/backbones/dinov2.py:340

src/model/unidepth/backbones/convnext.py:503

src/model/unidepth/backbones/convnext2.py:279

Functiongenerate_fourier_features

(x, max_freq=64, num_bands=16)

src/model/unidepth/layers/positional_encoding.py:89

Functiongenerate_heterogeneous_index_transpose

Generate an index that can be used to "transpose" the heterogeneous index. Applying the index a second time inverts the "transpose."

src/misc/heterogeneous_pairings.py:27

Methodget_bound

( self, bound: Literal["near", "far"], num_views: int, )

src/dataset/dataset_re10k_test.py:141

Methodget_bound

( self, bound: Literal["near", "far"], num_views: int, )

src/dataset/dataset_acid_test.py:138

← previous next →601–700 of 843, ranked by callers