MCPcopy Create free account

hub / github.com/MotrixLab/ADHMR / functions

Functions2,101 in github.com/MotrixLab/ADHMR

⨍ Functions 2,101◇ Types & classes 404
↓ 2 callersFunctionget_parents
(num_joints)
ADHMR/lib/utils/draw.py:256
↓ 2 callersFunctionget_process_groups
()
HMR-Scorer/common/utils/distribute_utils.py:136
↓ 2 callersMethodget_proposal_pos_embed
Get the position embedding of proposal.
HMR-Scorer/main/transformer_utils/mmpose/models/utils/transformer.py:966
↓ 2 callersFunctionget_rank
()
HMR-Scorer/common/utils/distribute_utils.py:131
↓ 2 callersFunctionget_state_dict
Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Keys
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/utils/utils.py:429
↓ 2 callersMethodget_subject
(self)
HMR-Scorer/data/Human36M/Human36M.py:67
↓ 2 callersMethodget_subsampling_ratio
(self)
HMR-Scorer/data/Human36M/Human36M.py:59
↓ 2 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
ADHMR/lib/models/hyponet.py:15
↓ 2 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
ADHMR/lib/models/scorenet.py:14
↓ 2 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
HMR-Scorer/common/nets/scorernet.py:17
↓ 2 callersFunctionget_torchvision_models
()
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/hrt_checkpoint.py:172
↓ 2 callersFunctionget_torchvision_models
()
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/utils/utils.py:180
↓ 2 callersMethodhalf_body_transform
(self, joints, joints_vis)
ADHMR/lib/utils/presets/simple_transform_3d_smpl_cam.py:607
↓ 2 callersMethodhalf_body_transform
(self, joints, joints_vis)
ADHMR/lib/utils/presets/simple_transform_3d_smpl_dpo.py:616
↓ 2 callersMethodhalf_body_transform
(self, joints, joints_vis)
ADHMR/lib/utils/presets/simple_transform_3d_smpl.py:580
↓ 2 callersMethodhalf_body_transform
(self, joints, joints_vis)
ADHMR/lib/utils/presets/simple_transform_3d_smpl_humandata.py:486
↓ 2 callersMethodhybrik
Inverse pass for the SMPL model Parameters ---------- pose_skeleton: torch.tensor, optional, shape Bx(J*3)
ADHMR/lib/models/layers/smpl/SMPL.py:220
↓ 2 callersMethodinit_weights
(self)
HMR-Scorer/main/transformer_utils/mmpose/models/utils/transformer.py:695
↓ 2 callersFunctioninverse_affine_transform
(transformed_pt, t)
ADHMR/lib/utils/transforms.py:1413
↓ 2 callersFunctionis_dist_avail_and_initialized
()
HMR-Scorer/common/utils/distribute_utils.py:117
↓ 2 callersFunctionkeypoints_from_regression
Get final keypoint predictions from regression vectors and transform them back to the image. Note: - batch_size: N - num_keyp
HMR-Scorer/main/transformer_utils/mmpose/core/evaluation/top_down_eval.py:441
↓ 2 callersFunctionlbs_get_twist
( betas: Tensor, pose: Tensor, v_template: Tensor, shapedirs: Tensor, posedirs: Tensor,
HMR-Scorer/common/utils/smplx/smplx/lbs.py:971
↓ 2 callersMethodload
(self, load_path)
HMR-Scorer/data/InstaVariety_DPO.py:166
↓ 2 callersMethodload
(self, load_path)
HMR-Scorer/data/Human36M_DPO.py:170
↓ 2 callersMethodload_data
(self)
HMR-Scorer/data/Human36M/Human36M.py:77
↓ 2 callersMethodload_dpo_pt
Load all image paths and labels from json annotation files into buffer.
ADHMR/lib/dataset/InstaVariety_dpo.py:116
↓ 2 callersMethodload_dpo_pt
Load all image paths and labels from json annotation files into buffer.
ADHMR/lib/dataset/InstaVariety_dpo.py:231
↓ 2 callersFunctionload_model
(model,state)
ADHMR/lib/utils/function.py:208
↓ 2 callersFunctionload_state_dict
Load state_dict to a module. This method is modified from :meth:`torch.nn.Module.load_state_dict`. Default value for ``strict`` is set to ``Fa
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/utils/utils.py:51
↓ 2 callersMethodmake_res_layer
Make a ResLayer.
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/resnet.py:564
↓ 2 callersMethodmask_weights
(self, layer,mask,mshape)
ADHMR/lib/models/scorenet.py:177
↓ 2 callersMethodmulti_head_attention_forward
( self, query: Tensor, key: Tensor, value: Tensor, embed_dim_to_check:
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/modules/multihead_attention.py:127
↓ 2 callersFunctionnonlinearity
(x)
ADHMR/lib/models/hyponet.py:58
↓ 2 callersMethodnorm1
nn.Module: the normalization layer named "norm1"
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/resnet.py:227
↓ 2 callersFunctionoks_iou
Calculate oks ious. Args: g: Ground truth keypoints. d: Detected keypoints. a_g: Area of the ground truth object.
HMR-Scorer/main/transformer_utils/mmpose/core/post_processing/nms.py:51
↓ 2 callersMethodparse
Group keypoints into poses given heatmap and tag. Note: batch size: N number of keypoints: K heatmap heig
HMR-Scorer/main/transformer_utils/mmpose/core/post_processing/group.py:368
↓ 2 callersFunctionparse_require_file
(fpath)
HMR-Scorer/main/transformer_utils/setup.py:83
↓ 2 callersFunctionpost_dark_udp
DARK post-pocessing. Implemented by udp. Paper ref: Huang et al. The Devil is in the Details: Delving into Unbiased Data Processing for Human
HMR-Scorer/main/transformer_utils/mmpose/core/evaluation/top_down_eval.py:335
↓ 2 callersMethodprint_scorer_eval_result
(self, eval_result)
HMR-Scorer/data/dataset.py:121
↓ 2 callersFunctionprocess_db_coord
(joint_img, joint_cam, joint_valid, do_flip, img_shape, flip_pairs, img2bb_trans, rot, sr
ADHMR/lib/utils/preprocessing.py:188
↓ 2 callersFunctionprocess_human_model_output
(human_model_param, cam_param, do_flip, img_shape, img2bb_trans, rot, human_model_type, joint_img=None)
ADHMR/lib/utils/preprocessing.py:244
↓ 2 callersFunctionprocess_human_model_output_clean
(human_model_param, cam_param, do_flip, img_shape, img2bb_trans, rot, human_model_type, joint_img=None)
HMR-Scorer/common/utils/preprocessing.py:596
↓ 2 callersFunctionprocess_pred
(pred, dataset, multi_n, type='H36M', save_path=None, use_score=False)
ADHMR/lib/utils/function.py:270
↓ 2 callersMethodprojection
(self, xyz, camera, f)
ADHMR/lib/utils/presets/simple_transform_3d_cam_eft.py:556
↓ 2 callersFunctionquat_to_rotmat
Convert quaternion coefficients to rotation matrix. Args: quat: size = [B, 4] 4 <===>(w, x, y, z) Returns: Rotation matrix cor
ADHMR/lib/models/layers/smpl/lbs.py:1688
↓ 2 callersMethodregister
(self, module)
HMR-Scorer/main/transformer_utils/mmpose/utils/hooks.py:13
↓ 2 callersFunctionrender_mesh
(height, width, meshes, face, cam_param)
ADHMR/lib/utils/draw.py:55
↓ 2 callersFunctionrender_multi_pose
(img, body_model_params, body_model, cameras
HMR-Scorer/main/render.py:99
↓ 2 callersFunctionrot_aa
Rotate axis angle parameters.
ADHMR/lib/utils/transforms.py:1063
↓ 2 callersFunctionrot_mat_to_euler
(rot_mats)
HMR-Scorer/common/utils/smplx/smplx/utils.py:119
↓ 2 callersFunctionrotate_2d
(pt_2d, rot_rad)
ADHMR/lib/utils/preprocessing.py:143
↓ 2 callersFunctionrotate_2d
(pt_2d, rot_rad)
HMR-Scorer/common/utils/preprocessing.py:156
↓ 2 callersFunctionrotation_matrix_to_quaternion
This function is borrowed from https://github.com/kornia/kornia Convert 3x4 rotation matrix to 4d quaternion vector This algorithm is b
ADHMR/lib/models/layers/smpl/lbs.py:1605
↓ 2 callersFunctionrotmat_to_quat
(rotation_matrix)
ADHMR/lib/models/layers/smpl/lbs.py:1593
↓ 2 callersMethodsave_cache
(self, annot_path_cache, datalist)
HMR-Scorer/data/humandata.py:130
↓ 2 callersMethodsave_cache
(self, annot_path_cache, datalist)
HMR-Scorer/data/Human36M_DPO.py:56
↓ 2 callersMethodseperate_sigma_from_score
(self, score)
HMR-Scorer/main/transformer_utils/mmpose/models/detectors/poseur.py:127
↓ 2 callersFunctionsmoothing_factor
(t_e, cutoff)
HMR-Scorer/main/transformer_utils/mmpose/core/post_processing/one_euro_filter.py:11
↓ 2 callersFunctionsmoothing_factor
(t_e, cutoff)
HMR-Scorer/main/transformer_utils/mmpose/core/post_processing/temporal_filters/one_euro_filter.py:13
↓ 2 callersFunctionto_numpy
(tensor)
ADHMR/lib/utils/transforms.py:120
↓ 2 callersMethodtrain
Convert the model into training mode.
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/vit.py:324
↓ 2 callersMethodvalues
(self)
ADHMR/lib/utils/smplx/smplx/utils.py:47
↓ 2 callersFunctionvectors2rotmat
(vec_rest, vec_final, dtype)
HMR-Scorer/common/utils/smplx/smplx/lbs.py:888
↓ 2 callersFunctionvisualize
(results,draw_num,save_path,detection_all=None,input_type='image')
ADHMR/lib/utils/inference.py:83
↓ 2 callersMethodwindow_partition
Args: x: (B, H, W, C) Returns: windows: (num_windows*B, window_size, window_size, C)
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/swin.py:264
↓ 2 callersFunctionworld2cam
(world_coord, R, t)
HMR-Scorer/common/utils/transforms.py:24
↓ 1 callersMethod__init__
(self,bs)
ADHMR/lib/utils/inference.py:133
↓ 1 callersMethod__init__
(self, cfg, transform, data_split, dpo_ann_file, dpo_root='./data/dpo')
ADHMR/lib/dataset/InstaVariety_dpo.py:13
↓ 1 callersMethod__init__
(self, cfg, neighbour_matrix=None)
ADHMR/lib/models/scorenet.py:116
↓ 1 callersMethod__init__
(self, **kwargs)
ADHMR/lib/models/layers/smpl/SMPL.py:21
↓ 1 callersMethod__init__
(self, transform, data_split)
HMR-Scorer/data/GTA_Human2/GTA_Human2.py:19
↓ 1 callersMethod__init__
(self, transform, data_split)
HMR-Scorer/data/HI4D/HI4D.py:22
↓ 1 callersMethod__init__
(self, transform, data_split)
HMR-Scorer/data/RenBody_HiRes/RenBody_HiRes.py:20
↓ 1 callersMethod__init__
(self, t0, x0, dx0, min_cutoff, beta, d_cutoff=1.0)
HMR-Scorer/main/transformer_utils/mmpose/core/post_processing/temporal_filters/one_euro_filter.py:24
↓ 1 callersMethod__init__
(self, dataloader, start=None, interval=1,
HMR-Scorer/main/transformer_utils/mmpose/core/evaluation/eval_hooks.py:16
↓ 1 callersMethod__init__
(self, depth, groups=32, width_per_group=4, **kwargs)
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/resnext.py:152
↓ 1 callersMethod__init__
(self, downsample_times=4, num_stacks=1, out_channels=34,
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/hourglass_ae.py:102
↓ 1 callersMethod__init__
(self, in_channels, stem_channels=1024, num_blocks=2,
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/tcn.py:179
↓ 1 callersMethod__init__
(self, extra, in_channels=3, conv_cfg=None,
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/hrnet.py:275
↓ 1 callersMethod__init__
(self, depth, se_ratio=16, **kwargs)
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/seresnet.py:118
↓ 1 callersMethod__init__
(self, widen_factor=1.0, out_indices=(3, ), frozen_stages=-
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/shufflenet_v2.py:158
↓ 1 callersMethod__init__
(self, in_channels, out_channels, groups=3,
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/shufflenet_v1.py:47
↓ 1 callersMethod__init__
(self, depth, groups=32, width_per_group=4, **kwargs)
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/seresnext.py:158
↓ 1 callersMethod__init__
( self, extra, in_channels=3, conv_cfg=None, norm_cfg=dict(type="BN",
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/hrt.py:322
↓ 1 callersMethod__init__
(self, in_channels, out_channels, feat_channels=128,
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/cpm.py:86
↓ 1 callersMethod__init__
(self, widen_factor=1., out_indices=(7, ), frozen_stages=-1
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/mobilenet_v2.py:130
↓ 1 callersMethod__init__
(self, sample_ratio, embed_dim, dim_out, k=5)
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/tcformer.py:27
↓ 1 callersMethod__init__
(self, downsample_times=5, num_stacks=2, stage_channels=(25
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/hourglass.py:120
↓ 1 callersMethod__init__
(self, num_feats, temperature=10000, normalize=False,
HMR-Scorer/main/transformer_utils/mmpose/models/utils/positional_encoding.py:33
↓ 1 callersMethod__init__
(self, gan_type, real_label_val=1.0, fake_label_val=0.0,
HMR-Scorer/main/transformer_utils/mmpose/models/losses/mesh_loss.py:263
↓ 1 callersMethod__init__
(self, scorehypo_cfg, neighbour_matrix=None)
HMR-Scorer/common/nets/scorernet.py:120
↓ 1 callersFunction_allreduce_coalesced
Allreduce parameters as a whole.
HMR-Scorer/main/transformer_utils/mmpose/core/utils/dist_utils.py:12
↓ 1 callersMethod_check
Check input to avoid ValueError.
HMR-Scorer/main/transformer_utils/mmpose/models/misc/discriminator.py:38
↓ 1 callersMethod_check_branches
(self, num_branches, blocks, num_blocks, num_inchannels, num_channels)
ADHMR/lib/models/hrnet.py:121
↓ 1 callersMethod_check_branches
Check input to avoid ValueError.
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/hrnet.py:54
↓ 1 callersMethod_check_branches
Check input to avoid ValueError.
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/litehrnet.py:567
↓ 1 callersMethod_check_branches
(self, num_branches, num_blocks, in_channels, num_channels)
HMR-Scorer/main/transformer_utils/mmpose/models/backbones/hrt.py:75
↓ 1 callersMethod_check_load_keypoints
Check and load ground-truth keypoints
ADHMR/lib/dataset/mscoco.py:282
↓ 1 callersMethod_check_load_keypoints
Check and load ground-truth keypoints
ADHMR/lib/dataset/surreal.py:273
↓ 1 callersMethod_collate_pose
Collate the pose results to pose sequences. Args: results (list[list[dict]]): The pose results of multiple frames. Retur
HMR-Scorer/main/transformer_utils/mmpose/core/post_processing/smoother.py:74
← previousnext →301–400 of 2,101, ranked by callers