Functions — github.com/cvlab-kaist/PF3plat

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

Functions843 in github.com/cvlab-kaist/PF3plat

⨍ Functions 843◇ Types & classes 197↳ Endpoints 2

Methodset_shapes

(self, shapes: tuple[int, int])

src/model/unidepth/unidepthv2/decoder.py:86

Methodset_shapes

(self, shapes: tuple[int, int])

src/model/unidepth/unidepthv2/decoder.py:127

Functionsetup_multi_processes

Setup multi-processing environment variables.

src/model/unidepth/utils/distributed.py:57

Functionsetup_slurm

Initialize slurm distributed training environment. If argument ``port`` is not specified, then the master port will be system environment vari

src/model/unidepth/utils/distributed.py:102

Methodshuffle

(self, lst: list)

src/dataset/dataset_re10k_test.py:75

Methodshuffle

(self, lst: list)

src/dataset/dataset_acid_test.py:75

Functionsoft_argmax

r"""SFNet: Learning Object-aware Semantic Flow (Lee et al.)

src/flow_util.py:843

Functionsoftmax_stack

(tensors, temperature=1.0)

src/model/unidepth/utils/misc.py:28

Functionspherical_to_euclidean

(spherical_tensor)

src/model/unidepth/utils/geometric.py:74

Functionsplit_feature

(feature, num_splits=2, channel_last=False, )

src/flow_util.py:33

Methodstate_dict

(self, *args, **kwargs)

src/model/unidepth/utils/ema_torch.py:50

Methodstore

(self, *args, **kwargs)

src/model/unidepth/utils/ema_torch.py:34

Functionsum_stack

(tensors)

src/model/unidepth/utils/misc.py:40

Functionsync_string_across_gpus

(keys: list[str], device, dim=0)

src/model/unidepth/utils/distributed.py:166

Methodtest_step

(self, batch, batch_idx)

src/model/model_wrapper.py:243

Methodtest_step

(self, batch, batch_idx)

src/evaluation/evaluation_index_generator.py:47

Methodtest_step

(self, batch, batch_idx)

src/evaluation/metric_computer.py:22

Functiontimestep_embedding

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be

src/model/encoder/costvolume/ldm_unet/util.py:151

Methodto

(self, *args, **kwargs)

src/model/unidepth/utils/ema_torch.py:47

Functionto_cpu

(infos)

src/model/unidepth/utils/misc.py:414

Methodtrain

(self, mode=True)

src/model/unidepth/backbones/dinov2.py:346

Methodtrain_dataloader

(self)

src/dataset/data_module.py:90

Methodtraining_step

(self, batch, batch_idx)

src/model/model_wrapper.py:139

Methodtrajectory_fn

(t)

src/model/model_wrapper.py:607

Functiontransform_points

src/model/encoder/costvolume/ldm_unet/attention.py:13

Functionunnormalise_and_convert_mapping_to_flow

(map)

src/flow_util.py:863

Functionunproject_points

Unprojects a batch of depth maps to 3D point clouds using camera intrinsics. Args: depth (torch.Tensor): Batch of depth maps of shap

src/model/unidepth/utils/geometric.py:115

Methodupdate

(self, *args, **kwargs)

src/model/unidepth/utils/ema_torch.py:28

Methodval_dataloader

(self)

src/dataset/data_module.py:103

Methodvalidation_step

(self, batch, batch_idx)

src/model/model_wrapper.py:417

Methodversion

(self)

src/misc/LocalLogger.py:23

Functionvis_disparity

(disp)

src/visualization/vis_depth.py:14

Methodvisualize

( self, context: BatchedViews, global_step: int, )

src/model/encoder/visualization/encoder_visualizer_costvolume.py:36

Functionvisualize_points

Visualizes points on a blank image. Args: - points (Tensor): The xy coordinates of points to visualize. Shape: [N, 2]. - image_s

src/flow_util.py:161

Methodvisualize_probabilities

( self, context_images: Float[Tensor, "batch view 3 height width"], sampling: None,

src/model/encoder/visualization/encoder_visualizer_costvolume.py:301

Functionvit_base

(patch_size=16, num_register_tokens=0, export=False, **kwargs)

src/model/unidepth/backbones/dinov2.py:374

Functionvit_large

(patch_size=16, num_register_tokens=0, export=False, **kwargs)

src/model/unidepth/backbones/dinov2.py:388

Functionvit_small

(patch_size=16, num_register_tokens=0, export=False, **kwargs)

src/model/unidepth/backbones/dinov2.py:360

Functionviz_depth_tensor

(disp, return_numpy=False, colormap='plasma')

src/visualization/vis_depth.py:22

Functionwarp

warp an image/tensor (im2) back to im1, according to the optical flow Args: x: [B, C, H, W] (im2) flo: [B, 2

src/flow_util.py:1016

Functionwarp_grid

warp an image/tensor (im2) back to im1, according to the optical flow Args: x: [B, C, H, W] (im2) flo: [B, 2

src/flow_util.py:1046

Functionworker_init_fn

(worker_id: int)

src/dataset/data_module.py:53

← previous801–843 of 843, ranked by callers