Functions — github.com/Tsinghua-MARS-Lab/SLAM-Former

hub / github.com/Tsinghua-MARS-Lab/SLAM-Former / functions

Functions601 in github.com/Tsinghua-MARS-Lab/SLAM-Former

⨍ Functions 601◇ Types & classes 107

↓ 1 callersFunctionget_world_size

()

src/croco/utils/misc.py:228

↓ 1 callersFunctionhomogenize_points

Convert batched points (xyz) to (xyz1).

src/slamformer/utils/geometry.py:116

↓ 1 callersMethodinit_weights

(self)

src/slamformer/models/dinov2/models/vision_transformer.py:174

↓ 1 callersMethodinitialize_weights

(self)

src/croco/models/croco.py:191

↓ 1 callersFunctioninterpolate_pos_embed

(model, checkpoint_model)

src/croco/models/pos_embed.py:80

↓ 1 callersMethodinterpolate_pos_encoding

(self, x, w, h)

src/slamformer/models/dinov2/models/vision_transformer.py:181

↓ 1 callersFunctionis_main_process

(accelerator: Accelerator)

src/croco/utils/misc.py:240

↓ 1 callersMethodis_other_viewpoint_overlapping

Check if a viewpoint is valid and overlaps significantly with a reference one.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:322

↓ 1 callersFunctionis_port_in_use

(host, port)

src/slamformer/utils/debug.py:36

↓ 1 callersMethodkf_detect

(self, image)

slam/demo.py:149

↓ 1 callersFunctionlist_replica_cad_baked_lighting_scenes

( base_output_dir, base_path=SCENES_DATASET["replica_cad_baked_lighting"] )

src/croco/datasets/habitat_sim/paths.py:52

↓ 1 callersFunctionlist_replica_scenes

(base_output_dir, base_path)

src/croco/datasets/habitat_sim/paths.py:77

↓ 1 callersFunctionlist_scenes_available

(base_output_dir, scenes_dataset_paths=SCENES_DATASET)

src/croco/datasets/habitat_sim/paths.py:141

↓ 1 callersFunctionload_crop_file

(path)

src/croco/datasets/crops/extract_crops_from_images.py:75

↓ 1 callersFunctionload_image

(path)

src/croco/datasets/crops/extract_crops_from_images.py:118

↓ 1 callersFunctionload_pairs_from_cache_file

(fname, root="")

src/croco/datasets/pairs_dataset.py:15

↓ 1 callersFunctionload_pairs_from_list_file

(fname, root="")

src/croco/datasets/pairs_dataset.py:28

↓ 1 callersFunctionload_ply

Load combined point cloud from PLY file.

slam/visualize_results.py:114

↓ 1 callersFunctionload_pointclouds

Load per-frame point clouds from npz files. Each npz file contains: - pointcloud: (H, W, 3) point positions - mask: (H, W) co

slam/visualize_results.py:68

↓ 1 callersFunctionload_trajectory

Load trajectory from TUM format file. TUM format: timestamp tx ty tz qx qy qz qw Returns: poses: (N, 4, 4) array of camera p

slam/visualize_results.py:34

↓ 1 callersFunctionlog_image

( entity_path: str, color_frame_b3hw: torch.Tensor, denormalize=True )

slam/rerun_helper/__init__.py:106

↓ 1 callersFunctionlog_source_data

(src_entity_path: str, src_data: Dict[str, Any])

slam/rerun_helper/__init__.py:38

↓ 1 callersFunctionlog_window

( entity_path: str, world_T_cam_44: torch.Tensor, K_44: torch.Tensor )

slam/rerun_helper/__init__.py:95

↓ 1 callersFunctionlook_at

Return camera pose looking at a given center point. Analogous of gluLookAt function, using OpenCV camera convention.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:96

↓ 1 callersFunctionmain

(args)

src/croco/pretrain.py:156

↓ 1 callersFunctionmain

(args)

src/croco/stereoflow/train.py:198

↓ 1 callersFunctionmain

(args)

src/croco/stereoflow/test.py:165

↓ 1 callersFunctionmain

(args)

src/croco/datasets/crops/extract_crops_from_images.py:46

↓ 1 callersFunctionmain

()

slam/visualize_results.py:397

↓ 1 callersFunctionmake_scratch

(in_shape, out_shape, groups=1, expand=False)

src/croco/models/dpt_block.py:22

↓ 1 callersMethodmedian

(self)

src/croco/utils/misc.py:62

↓ 1 callersFunctionnamed_apply

(fn: Callable, module: nn.Module, name="", depth_first=True, include_root=False)

src/slamformer/models/dinov2/models/vision_transformer.py:27

↓ 1 callersFunctionnormalize_depth_single

(depth_11hw, mask_11hw, robust=False)

slam/rerun_helper/generic_utils.py:42

↓ 1 callersFunctionpair

(t)

src/croco/models/dpt_block.py:18

↓ 1 callersMethodpairwise_cosine_similarity

(self, matrix)

src/slamformer/models/slamformer.py:180

↓ 1 callersFunctionparse_and_cache_all_pairs

(dname, data_dir="./data/")

src/croco/datasets/pairs_dataset.py:57

↓ 1 callersFunctionprepare_jobs

(pairs, num_levels, num_pairs_in_dir)

src/croco/datasets/crops/extract_crops_from_images.py:94

↓ 1 callersMethodprepare_pointcloud_rgb

Return RGB colors aligned to the model point grid.

slam/demo.py:382

↓ 1 callersMethodreset

(self)

src/croco/stereoflow/criterion.py:243

↓ 1 callersFunctionrope_2d_cpu

src/croco/models/curope/curope.cpp:11

↓ 1 callersMethodrotate_half

(x)

src/slamformer/models/layers/pos_embed.py:134

↓ 1 callersMethodrotate_half

(x)

src/croco/models/pos_embed.py:148

↓ 1 callersMethodrun

Run the viewer.

slam/visualize_results.py:390

↓ 1 callersMethodsample_other_random_viewpoint

Sample a random viewpoint close to an existing one, using the navmesh and a reference observed point.

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:271

↓ 1 callersMethodsave_framewise_pointclouds

(self, filename, pointclouds, frame_ids, conf_masks, colors)

slam/demo.py:500

↓ 1 callersMethodsave_result

if map_all is None: map_all = self.map

slam/demo.py:449

↓ 1 callersMethodspatial_transform

(self, img1, img2, flow, dname)

src/croco/stereoflow/augmentor.py:334

↓ 1 callersMethodsubmission_save_pairname

(self, pairname, prediction, outdir, time)

src/croco/stereoflow/datasets_flow.py:508

↓ 1 callersMethodsvd_orthogonalize

Convert 9D representation to SO(3) using SVD orthogonalization. Args: m: [BATCH, 3, 3] 3x3 matrices. Returns: [B

src/slamformer/models/layers/camera_head.py:74

↓ 1 callersMethodsynchronize_between_processes

(self, accelerator)

src/croco/utils/misc.py:124

↓ 1 callersMethodterminate

(self)

slam/demo.py:406

↓ 1 callersFunctiontrain_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, data_loader: Iterable, optimizer: torch.

src/croco/pretrain.py:311

↓ 1 callersFunctiontrain_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, metrics: torch.nn.Module, data_loader: I

src/croco/stereoflow/engine.py:26

↓ 1 callersFunctionupdate_vscode_launch_file

Update the .vscode/launch.json file with the new host and port.

src/slamformer/utils/debug.py:7

↓ 1 callersFunctionvalidate_one_epoch

( model: torch.nn.Module, criterion: torch.nn.Module, metrics: torch.nn.Module, data_loaders:

src/croco/stereoflow/engine.py:133

↓ 1 callersFunctionvis_disparity

(disp, m=None, M=None)

src/croco/stereoflow/datasets_stereo.py:964

↓ 1 callersFunctionwarp_kpts

Warp kpts0 from I0 to I1 with depth, K and Rt Also check covisibility and depth consistency. Depth is consistent if relative error < 0.2 (hard

src/slamformer/utils/geometry.py:155

↓ 1 callersFunctionwriteDsp5File

(disp, filename)

src/croco/stereoflow/datasets_stereo.py:956

↓ 1 callersFunctionwriteFlo5File

(flow, filename)

src/croco/stereoflow/datasets_flow.py:763

↓ 1 callersFunctionwriteFlowFile

writeFlowFile(flow,<FILENAME>) write flow to the file <FILENAME>. if <FILENAME> does not exist, an IOError is raised. if <FILENAME> does

src/croco/stereoflow/datasets_flow.py:703

↓ 1 callersFunctionwrite_cache_file

(fname, pairs, root="")

src/croco/datasets/pairs_dataset.py:42

↓ 1 callersFunctionwrite_config

(cfg, output_dir, name="config.yaml")

src/slamformer/models/dinov2/utils/config.py:32

↓ 1 callersMethodwrite_poses_to_file

(self, filename, poses, frame_ids)

slam/demo.py:489

FunctionPYBIND11_MODULE

src/croco/models/curope/curope.cpp:67

Method_

(event)

slam/visualize_results.py:186

Method__call__

(self, b, h, w, device)

src/slamformer/models/layers/pos_embed.py:170

Method__call__

( self, loss, optimizer, clip_grad=None, parameters=None, crea

src/croco/utils/misc.py:290

Method__call__

(self, img1, img2, disp, dataset_name)

src/croco/stereoflow/augmentor.py:229

Method__call__

(self, img1, img2, flow, dname)

src/croco/stereoflow/augmentor.py:390

Method__call__

(self, img1, img2)

src/croco/datasets/transforms.py:27

Method__call__

(self, x)

src/croco/models/masking.py:23

Method__call__

(self, b, h, w, device)

src/croco/models/blocks.py:329

Method__del__

(self)

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:253

Method__getattr__

(self, attr)

src/croco/utils/misc.py:109

Method__getitem__

(self, it)

src/slamformer/models/dinov2/utils/utils.py:83

Method__getitem__

(self, index)

src/croco/stereoflow/datasets_flow.py:68

Method__getitem__

(self, index)

src/croco/stereoflow/datasets_stereo.py:81

Method__getitem__

(self, index)

src/croco/datasets/pairs_dataset.py:140

Method__getitem__

(self, useless_idx)

src/croco/datasets/habitat_sim/multiview_habitat_sim_generator.py:343

Method__init__

( self, pos_type='rope100', decoder_size='large', retention_ra

src/slamformer/models/slamformer.py:31

Method__init__

( self, dim: int, num_heads: int, mlp_ratio: float = 4.0, qkv_bias: bo

src/slamformer/models/layers/block.py:261

Method__init__

( self, dim: int, num_heads: int, mlp_ratio: float = 4.0, qkv_bias: bo

src/slamformer/models/layers/block.py:381

Method__init__

( self, in_dim, out_dim, dec_embed_dim=512, depth=5, dec_num_h

src/slamformer/models/layers/transformer_head.py:10

Method__init__

(self, in_channels: int, out_channels: int = None, hidden_channels: int = None, padding_mode: str = 'replicate

src/slamformer/models/layers/conv_head.py:26

Method__init__

( self, dim: int, num_heads: int = 8, qkv_bias: bool = False, proj_bia

src/slamformer/models/layers/attention.py:122

Method__init__

( self, dim: int, num_heads: int = 8, qkv_bias: bool = False, proj_bia

src/slamformer/models/layers/attention.py:245

Method__init__

(self, freq=100.0, F0=1.0)

src/slamformer/models/layers/pos_embed.py:116

Method__init__

(self)

src/slamformer/models/layers/pos_embed.py:167

Method__init__

(self, in_channels, out_channels)

src/slamformer/models/layers/camera_head.py:11

Method__init__

(self, base_value, final_value, total_iters, warmup_iters=0, start_warmup_value=0, freeze_iters=0)

src/slamformer/models/dinov2/utils/utils.py:68

Method__init__

(self, multiple)

src/slamformer/models/dinov2/hub/utils.py:24

Method__init__

(self, drop_prob=None)

src/slamformer/models/dinov2/layers/drop_path.py:29

Method__init__

( self, dim: int, num_heads: int, mlp_ratio: float = 4.0, qkv_bias: bo

src/slamformer/models/dinov2/layers/block.py:43

Method__init__

( self, in_dim, out_dim, use_bn=False, nlayers=3, hidden_dim=2

src/slamformer/models/dinov2/layers/dino_head.py:13

Method__init__

( self, dim: int, init_values: Union[float, Tensor] = 1e-5, inplace: bool = Fa

src/slamformer/models/dinov2/layers/layer_scale.py:16

Method__init__

( self, dim: int, num_heads: int = 8, qkv_bias: bool = False, proj_bia

src/slamformer/models/dinov2/layers/attention.py:37

Method__init__

( self, in_features: int, hidden_features: Optional[int] = None, out_features:

src/slamformer/models/dinov2/layers/mlp.py:17

Method__init__

( self, in_features: int, hidden_features: Optional[int] = None, out_features:

src/slamformer/models/dinov2/layers/swiglu_ffn.py:55

Method__init__

( self, img_size: Union[int, Tuple[int, int]] = 224, patch_size: Union[int, Tuple[int,

src/slamformer/models/dinov2/layers/patch_embed.py:37

Method__init__

Args: img_size (int, tuple): input image size patch_size (int, tuple): patch size in_chans (int): number

src/slamformer/models/dinov2/models/vision_transformer.py:46

← previous next →201–300 of 601, ranked by callers