Functions — github.com/XunshanMan/MVGFormer

CodeHub MCPcopy Create free account

hub / github.com/XunshanMan/MVGFormer / functions

Functions561 in github.com/XunshanMan/MVGFormer

⨍ Functions 561◇ Types & classes 78

(self, in_planes, out_planes)

lib/mvn/models/v2v.py:21

(self, pool_size)

lib/mvn/models/v2v.py:46

(self, in_planes, out_planes, kernel_size, stride)

lib/mvn/models/v2v.py:55

lib/mvn/models/v2v.py:70

(self, config, device='cuda:0')

lib/mvn/models/triangulation.py:132

(self, config, device='cuda:0')

lib/mvn/models/triangulation.py:204

(self, focal_length=1000, height=512, width=960)

lib/smpl/renderer.py:37

(self, fc_layers, use_dropout, drop_prob, use_ac_func)

lib/smpl/smpl_common.py:119

(self, channels)

lib/smpl/smpl_common.py:133

(self, fc_layers, use_dropout, drop_prob, use_ac_func)

lib/smpl/smpl_common.py:171

lib/smpl/smpl_common.py:185

(self, joint_maps=None)

lib/smpl/smpl.py:108

(self, dtype=torch.float32, **kwargs)

lib/smpl/prior.py:68

(self, prior_folder='data', num_gaussians=8, dtype=DEFAULT_DTYPE, epsilon=1e-16,

lib/smpl/prior.py:116

(self, space_size, space_center, img_size, d_model=256, d_ffn=1024, dropout=

lib/models/mvp_decoder.py:50

(self, inplanes, planes, stride=1, downsample=None)

lib/models/pose_resnet.py:71

(self, block, layers, cfg, **kwargs)

lib/models/pose_resnet.py:111

Creates the matcher Params: cost_class: This is the relative weight of the classification error in the matching cost

lib/models/matcher.py:31

(self, backbone, cfg)

lib/models/multi_view_pose_transformer.py:115

Create the criterion. Parameters: num_classes: number of object categories, omitting the special no-object category

lib/models/multi_view_pose_transformer.py:499

(self, backbone, cfg)

lib/models/dq_transformer.py:126

(self, num_pos_feats=64, temperature=10000, normalize=False, scale=None)

lib/models/position_encoding.py:108

(self, num_pos_feats=256)

lib/models/position_encoding.py:151

lib/models/dq_decoder.py:73

(self, in_dim, hid_dim, layer_num)

lib/models/dq_decoder.py:98

(self, space_size, space_center, img_size, pose_embed_layer, d_model=256, d_ffn=1024,

lib/models/dq_decoder.py:249

Projective Attention Module :param d_model hidden dimension :param n_levels number of feature levels :param

lib/models/ops/modules/projattn.py:43

(self, window_size=20, fmt=None)

lib/models/util/misc.py:91

(self, delimiter="\t")

lib/models/util/misc.py:273

(self, tensors, mask: Optional[Tensor])

lib/models/util/misc.py:421

lib/dataset/samplers.py:62

lib/dataset/samplers.py:129

lib/dataset/shelf.py:252

lib/dataset/samplers.py:82

lib/dataset/samplers.py:149

lib/dataset/h36m.py:234

lib/dataset/campus.py:247

lib/dataset/JointsDataset.py:82

lib/dataset/panoptic.py:490

lib/mvn/datasets/human36m.py:113

lib/utils/misc.py:352

lib/models/util/misc.py:444

lib/utils/misc.py:104

lib/utils/misc.py:206

lib/models/util/misc.py:140

lib/models/util/misc.py:292

lib/dataset/JointsDataset.py:76

Methodabsolute2norm

(self, absolute_coords)

lib/models/matcher.py:65

Methodabsolute2norm

(self, absolute_coords)

lib/models/multi_view_pose_transformer.py:567

Functionaccuracy

Computes the precision@k for the specified values of k

lib/utils/misc.py:427

Methodadd_meter

(self, name, meter)

lib/utils/misc.py:218

Methodadd_meter

(self, name, meter)

lib/models/util/misc.py:304

Functionadd_result_to_retval

lib/mvn/datasets/human36m_preprocessing/collect-bboxes.py:76

Functionaffine_transform_pts

lib/utils/transforms.py:121

Functionaffine_transform_pts_cuda

lib/utils/transforms.py:128

Functionaffine_transform_pts_cuda_batch

(pts_batch, t_batch)

lib/utils/transforms.py:135

Functionall_gather

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

lib/utils/misc.py:113

Functionall_gather

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

lib/models/util/misc.py:197

lib/utils/misc.py:88

lib/models/util/misc.py:124

Functionbackproject_uv_to_depth

assume there are several layers of different depth, this function back project uv to all this layers :param uv: (2, N) :param camera:

lib/utils/cameras_cuda_col.py:110

Functionbatch_rodrigues

Convert axis-angle representation to rotation matrix. Args: theta: size = [B, 3] Returns: Rotation matrix corresponding to the

lib/smpl/utils.py:21

Functionbox_cxcywh_to_xyxy

lib/models/util/box_ops.py:19

Functionbox_xyxy_to_cxcywh

lib/models/util/box_ops.py:26

Functionbuild_matcher

lib/models/matcher.py:264

Functionbuild_position_encoding

lib/models/position_encoding.py:175

(eval_list, total_gt, method='score_sort')

lib/dataset/panoptic.py:564

Functioncalc_gradient_norm

(named_parameters)

lib/mvn/utils/misc.py:31

Functioncalc_reprojection_error_matrix

(keypoints_3d, keypoints_2d_list, proj_matricies)

lib/mvn/utils/multiview.py:271

Functioncamera_to_world_frame

Args x: 3xN points in camera coordinates R: 3x3 Camera rotation matrix T: 3x1 Camera translation parameters Returns

lib/utils/cameras_cuda_col.py:74

Functioncamera_to_world_frame

Args x: Nx3 points in camera coordinates R: 3x3 Camera rotation matrix T: 3x1 Camera translation parameters Returns

lib/utils/cameras.py:241

Methodcoco2campus3D

transform coco order(our method output) 3d pose to shelf dataset order with interpolation :param coco_pose: np.array with sha

lib/dataset/campus.py:331

Methodcoco2shelf3D

transform coco order(our method output) 3d pose to shelf dataset order with interpolation :param coco_pose: np.array with sha

lib/dataset/shelf.py:335

Functioncollate_fn

lib/utils/misc.py:297

Functioncollate_fn

lib/mvn/datasets/utils.py:8

Functioncollate_fn

lib/models/util/misc.py:384

Functionconfig_to_str

lib/mvn/utils/misc.py:9

Functioncount_valid_queries

(outputs_coords, num_joints)

lib/models/dq_transformer.py:773

Functioncreate_prior

(prior_type, **kwargs)

lib/smpl/prior.py:50

(img, center, scale, output_size, rot=0)

lib/utils/transforms.py:159

Methoddecompose

lib/utils/misc.py:349

Methoddecompose

lib/models/util/misc.py:441

Functiondeform_backward

lib/models/ops/src/deform.h:52

Functiondeform_core_pytorch

(value, value_spatial_shapes, sampling_locations, attention_weights)

lib/models/ops/functions/deform_func.py:68

Functiondeform_cpu_backward

lib/models/ops/src/cpu/deform_cpu.cpp:40

Functiondeform_cpu_forward

lib/models/ops/src/cpu/deform_cpu.cpp:28

Functiondeform_forward

lib/models/ops/src/deform.h:31

Functiondraw_2d_pose_cv2

(keypoints, canvas, kind='cmu', keypoints_mask=None, point_size=2, point_color=(255, 255, 255), line_width=1,

lib/mvn/utils/vis.py:301

Functiondraw_3d_pose

(keypoints, ax, keypoints_mask=None, kind='cmu', radius=None, root=None, point_size=2, line_width=2, draw_conn

lib/mvn/utils/vis.py:355

Methoddraw_skeleton

Draw human skeleton. :ax: <matplotlib.axes> the axes to draw the skeleton :pts: <numpy.ndarray> of n_joints

lib/structural/structural_triangulation.py:62

(self, preds, recall_threshold=500)

lib/dataset/shelf.py:255

(self, preds, recall_threshold=500)

lib/dataset/campus.py:250

(self, cfg, preds, output_dir, *args, **kwargs)

lib/dataset/JointsDataset.py:79

(self, preds, method='score_sort')

lib/dataset/panoptic.py:493

(self, keypoints_3d_predicted, split_by_subject=False, transfer_cmu_to_human36m=False, transfer_human36m_to_hu

lib/mvn/datasets/human36m.py:237

Methodevaluate_by_actions

(self, per_pose_error, mask=None)

lib/mvn/datasets/human36m.py:192

Methodextrinsics

lib/mvn/utils/multiview.py:51

Functionfilter_with_prob

(output, reference_points, query_pos_in, outputs_class, num_joints)

lib/models/dq_decoder.py:1201

Functionflip_back

ouput_flipped: numpy.ndarray(batch_size, num_joints, height, width)

lib/utils/transforms.py:30

Functionfliplr_joints

lib/utils/transforms.py:47

← previous next →301–400 of 561, ranked by callers