MCPcopy Create free account

hub / github.com/Xuehao-Gao/GUESS / functions

Functions912 in github.com/Xuehao-Gao/GUESS

↓ 3 callersFunctionquaternion_raw_multiply
Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part
mld/tools/geometry.py:355
↓ 3 callersFunctionquaternion_raw_multiply
Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part
mld/utils/rotation_conversions.py:340
↓ 3 callersFunctionquaternion_raw_multiply
Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part
mld/data/a2m/utils/rotation_conversions.py:340
↓ 3 callersFunctionrecover_root_rot_pos
(data)
mld/data/humanml/scripts/motion_process.py:362
↓ 3 callersFunctionremove_chumpy_dep
(dico)
prepare/merge_smplh_mano.py:30
↓ 3 callersMethodrenorm4t2m
(self, features)
mld/data/Kit.py:49
↓ 3 callersFunctionsubsample
(num_frames, last_framerate, new_framerate)
mld/utils/temos_utils.py:104
↓ 3 callersFunctionto_torch
(ndarray)
mld/data/a2m/utils/misc.py:13
↓ 2 callersMethodDatastruct
(self, **kwargs)
mld/transforms/xyz.py:15
↓ 2 callersFunctionLinearBlock
(in_dim, out_dim, dropout=None, norm='none', acti='relu')
mld/models/operator/blocks.py:137
↓ 2 callersFunctionNormalInDirection
(normal, direction, limit=0.5)
mld/render/blender/joints.py:363
↓ 2 callersMethod__init__
(self, dtype=DEFAULT_DTYPE, reduction='sum', **kwargs)
mld/transforms/joints2rots/prior.py:91
↓ 2 callersMethod__init__
(self, in_channels, num_class, kintree_path, graph_args, edge_importance_weighting, **kwargs)
mld/models/architectures/uestc_stgcn.py:26
↓ 2 callersMethod__init__
(self, ablation, nfeats: int, latent_dim: list = [1, 256],
mld/models/architectures/actor_vae.py:13
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
mld/tools/geometry.py:190
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
mld/utils/rotation_conversions.py:175
↓ 2 callersFunction_angle_from_tan
Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:
mld/data/a2m/utils/rotation_conversions.py:175
↓ 2 callersMethod_get_action_view_subject_side
(self, videopath)
mld/data/a2m/uestc.py:230
↓ 2 callersFunction_get_activation_fn
Return an activation function given a string
mld/models/operator/cross_attention.py:404
↓ 2 callersFunction_get_clone
(module)
mld/models/operator/cross_attention.py:384
↓ 2 callersFunction_index_from_letter
(letter: str)
mld/tools/geometry.py:223
↓ 2 callersFunction_index_from_letter
(letter: str)
mld/utils/rotation_conversions.py:208
↓ 2 callersFunction_index_from_letter
(letter: str)
mld/data/a2m/utils/rotation_conversions.py:208
↓ 2 callersMethod_update_loss
(self, loss: str, outputs, inputs)
mld/models/losses/actor.py:80
↓ 2 callersMethodaction_to_action_name
(self, action)
mld/data/a2m/dataset.py:88
↓ 2 callersFunctionalign_by_parts
(joints, align_inds=None)
mld/models/metrics/utils.py:347
↓ 2 callersFunctionangle_prior
Angle prior that penalizes unnatural bending of the knees and elbows
mld/transforms/joints2rots/customloss.py:15
↓ 2 callersFunctioncalc_output_padding
(input_shape, output_shape)
mld/models/operator/conv2d_gradfix.py:122
↓ 2 callersFunctioncalculate_top_k
(mat, top_k)
mld/models/metrics/utils.py:62
↓ 2 callersFunctioncamera_fitting_loss_3d
Loss function for camera optimization.
mld/transforms/joints2rots/customloss.py:185
↓ 2 callersFunctioncollate_tensors
(batch)
mld/utils/tensors.py:11
↓ 2 callersFunctioncolored_material_diffuse_BSDF
(r, g, b, a=1, roughness=0.127451)
mld/render/blender/materials.py:10
↓ 2 callersMethodcompute
(self, sanity_flag)
mld/models/metrics/mm.py:34
↓ 2 callersFunctioncompute_mpjpe
Mean per-joint position error (i.e. mean Euclidean distance) often referred to as "Protocol #1" in many papers.
mld/models/metrics/utils.py:321
↓ 2 callersFunctioncont6d_to_matrix_np
(cont6d)
mld/data/humanml/common/quaternion.py:339
↓ 2 callersFunctioncould_use_op
(input)
mld/models/operator/conv2d_gradfix.py:78
↓ 2 callersFunctioncylinder_sphere_between
(t1, t2, r, mat)
mld/render/blender/joints.py:203
↓ 2 callersFunctioneuclidean_distance_matrix
Params: -- matrix1: N1 x D -- matrix2: N2 x D Returns: -- dist: N1 x N2 dist[i, j] == distance(matrix1[i], matrix2[j])
mld/models/metrics/utils.py:26
↓ 2 callersMethodextract
(self, features: Tensor)
mld/transforms/joints2jfeats/rifke.py:136
↓ 2 callersFunctionfoot_detect
(positions, thres)
mld/data/humanml/scripts/motion_process.py:43
↓ 2 callersFunctionfreeze_params
Freeze the parameters of this module, i.e. do not update them during training :param module: freeze parameters of this module
mld/models/tools/tools.py:29
↓ 2 callersFunctionget_acti_layer
(acti='relu', inplace=True)
mld/models/operator/blocks.py:39
↓ 2 callersMethodget_action
(self, ind)
mld/data/a2m/dataset.py:85
↓ 2 callersFunctionget_activation
(activation_type)
mld/models/architectures/tools/embeddings.py:8
↓ 2 callersFunctionget_collate_fn
(name, phase="train")
mld/data/get_data.py:55
↓ 2 callersFunctionget_cont6d_params
(positions)
mld/data/humanml/scripts/motion_process.py:98
↓ 2 callersFunctionget_dropout_layer
(dropout=None)
mld/models/operator/blocks.py:68
↓ 2 callersMethodget_label_sample_batch
(self, labels)
mld/data/a2m/dataset.py:259
↓ 2 callersMethodget_mean_length_label
(self, label)
mld/data/a2m/dataset.py:272
↓ 2 callersFunctionget_mean_std
(phase, cfg, dataset_name)
mld/data/get_data.py:12
↓ 2 callersFunctionget_norm_layer
(norm='none', norm_dim=None)
mld/models/operator/blocks.py:53
↓ 2 callersMethodget_offsets_joints
(self, joints)
mld/data/humanml/common/skeleton.py:43
↓ 2 callersFunctionget_renderer
(width, height, cam_pose)
mld/render/renderer.py:173
↓ 2 callersFunctionget_rifke
Local pose
mld/data/humanml/scripts/motion_process.py:68
↓ 2 callersMethodget_sample_set
(self, overrides={})
mld/data/base.py:30
↓ 2 callersFunctiongmof
Geman-McClure error function
mld/transforms/joints2rots/customloss.py:6
↓ 2 callersFunctionhessian_penalty
Official PyTorch Hessian Penalty implementation. Note: If you want to regularize multiple network activations simultaneously, you need to
mld/models/tools/hessian_penalty.py:29
↓ 2 callersMethodinitHidden
(self, num_samples, layer)
mld/models/architectures/humanact12_gru.py:51
↓ 2 callersMethodinverse
(self, joints: Tensor)
mld/transforms/rots2joints/smplh.py:132
↓ 2 callersFunctionlengths_to_mask
(lengths)
mld/data/utils.py:4
↓ 2 callersFunctionmatrix_to
(newtype, rotations)
mld/utils/easyconvert.py:38
↓ 2 callersFunctionmesh_detect
(data)
mld/render/blender/tools.py:5
↓ 2 callersMethodmm_mode
(self, mm_on=True)
mld/data/Kit.py:59
↓ 2 callersFunctionnorm_cdf
(x)
mld/models/architectures/vision_transformer.py:88
↓ 2 callersFunctionperspective_projection
This function computes the perspective projection of a set of points. Input: points (bs, N, 3): 3D points rotation (bs, 3, 3)
mld/transforms/joints2rots/customloss.py:24
↓ 2 callersFunctionplot_3d_motion_dico
(x)
mld/render/visualize.py:46
↓ 2 callersFunctionplys2npy
(ply_dir, out_dir)
scripts/plys2npy.py:32
↓ 2 callersFunctionprocess_file
Uniform Skeleton
mld/data/humanml/scripts/motion_process.py:169
↓ 2 callersFunctionqeuler
Convert quaternion(s) q to Euler angles. Expects a tensor of shape (*, 4), where * denotes any number of dimensions. Returns a tensor of
mld/data/humanml/common/quaternion.py:76
↓ 2 callersFunctionqfix
Enforce quaternion continuity across the time dimension by selecting the representation (q or -q) with minimal distance (or, equivalently, ma
mld/data/humanml/common/quaternion.py:149
↓ 2 callersFunctionquaternion_to_cont6d
(quaternions)
mld/data/humanml/common/quaternion.py:314
↓ 2 callersFunctionquaternion_to_cont6d_np
(quaternions)
mld/data/humanml/common/quaternion.py:308
↓ 2 callersFunctionquaternion_to_matrix
Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten
mld/tools/geometry.py:52
↓ 2 callersFunctionquaternion_to_matrix
Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten
mld/utils/rotation_conversions.py:37
↓ 2 callersFunctionquaternion_to_matrix
Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten
mld/data/a2m/utils/rotation_conversions.py:37
↓ 2 callersFunctionquaternion_to_matrix
Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as tens
mld/data/humanml/common/quaternion.py:274
↓ 2 callersFunctionreduction
(x)
mld/models/tools/hessian_penalty.py:125
↓ 2 callersMethodrender
(self, img, verts, cam, angle=None, axis=None, mesh_filename=None, color=[1.0, 1.0, 0.9], cam_p
mld/render/renderer.py:108
↓ 2 callersFunctionrender_video
(meshes, key, action, renderer, savepath,
mld/render/rendermotion.py:18
↓ 2 callersFunctionsave_image
(image_numpy, image_path)
mld/data/humanml/utils/utils.py:22
↓ 2 callersFunctionsphere_between
(t1, t2, mat, factor=1)
mld/render/blender/joints.py:244
↓ 2 callersFunctionsubsample
(num_frames, last_framerate, new_framerate)
mld/data/sampling/framerate.py:5
↓ 2 callersFunctionto_matrix
(oldtype, rotations)
mld/utils/easyconvert.py:57
↓ 2 callersMethodtrain_diffusion_forward
(self, batch)
mld/models/modeltype/mld.py:665
↓ 2 callersMethodtrain_vae_forward
(self, batch)
mld/models/modeltype/mld.py:552
↓ 2 callersMethodwith_pos_embed
(self, tensor, pos: Optional[Tensor])
mld/models/operator/cross_attention.py:256
↓ 1 callersFunctionConvLayers
returns a list of [pad, conv] => should be += to some list, then apply sequential
mld/models/operator/blocks.py:75
↓ 1 callersFunctionGoingDown
(normal, limit=0.5)
mld/render/blender/joints.py:371
↓ 1 callersFunctionGoingUp
(normal, limit=0.5)
mld/render/blender/joints.py:367
↓ 1 callersFunctionRodrigues
(rotvec)
scripts/fbx_output.py:81
↓ 1 callersMethod__init__
(self, levels)
mld/tools/logging.py:6
↓ 1 callersMethod__init__
(self, background=None, resolution=(224, 224), bg_color=[0, 0, 0, 0.5], orig_img=False, wireframe=False, cam_p
mld/render/renderer.py:52
↓ 1 callersMethod__init__
(self, input_size, hidden_size, output_size)
mld/models/architectures/t2m_motionenc.py:7
↓ 1 callersMethod__init__
(self, ablation, nfeats: int = 263, condition: str = "text"
mld/models/architectures/mld_denoiser.py:18
↓ 1 callersMethod__init__
(self, modeltype, njoints, nfeats, num_frames, num_classes, translation, pose_rep, glob, glob_rot,
mld/models/architectures/fc.py:7
↓ 1 callersMethod__init__
(self)
mld/models/losses/temos.py:175
↓ 1 callersMethod__init__
(self)
mld/models/losses/actor.py:98
↓ 1 callersMethod__init__
(self)
mld/models/losses/mld.py:182
↓ 1 callersMethod__init__
(self)
mld/models/losses/tmost.py:190
↓ 1 callersMethod_get_t2m_evaluator
load T2M text encoder and motion encoder for evaluating
mld/models/modeltype/mld.py:177
← previousnext →101–200 of 912, ranked by callers